Dataset Viewer
Auto-converted to Parquet Duplicate
id
int64
1
52.9k
messages
listlengths
3
3
1
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
2
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
3
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
4
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
5
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
6
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
7
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
8
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
9
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
10
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
11
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
12
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
13
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
14
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
15
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
16
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
17
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
18
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
19
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
20
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
21
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
22
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
23
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
24
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
25
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
26
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
27
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
28
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
29
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
30
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
31
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
32
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
33
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
34
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
35
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
36
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
37
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
38
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
39
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
40
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
41
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
42
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
43
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
44
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
45
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
46
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
47
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
48
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
49
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
50
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
51
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
52
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
53
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
54
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
55
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
56
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
57
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
58
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
59
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
60
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
61
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
62
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
63
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
64
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
65
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
66
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
67
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
68
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
69
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
70
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
71
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
72
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
73
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
74
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
75
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
76
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
77
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
78
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
79
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
80
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
81
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
82
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
83
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
84
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
85
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
86
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
87
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
88
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
89
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
90
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
91
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
92
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
93
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
94
[ { "role": "system", "content": "You are a strict whitelist-only detector for specific entities.\nGiven the user's text, return ONLY a JSON with keys\nYou must output text in JSON format.\nInput : You receive an arbitrary text\nOutput : \n{\n \"text\": \"<original input text verbatim>\",\n \"has_sensitive\...
End of preview. Expand in Data Studio

Sentinel KR Sensitive Entities (Synthetic) v3

Overview

Sentinel KR Sensitive Entities (Synthetic) v3 is a Korean synthetic (AI-generated) dataset for whitelist-only sensitive-entity detection in DLP / LLM guardrail scenarios.

All sensitive values in this dataset (e.g., phone numbers, emails, IDs, tokens, keys) are artificially generated by AI and do not come from real individuals, real incidents, or collected private datasets.

Any resemblance to real persons or real identifiers is purely coincidental.

Intended Use

  • Train / evaluate models that detect sensitive information before sending prompts or text payloads to external LLM services.
  • Build DLP-style guardrails (block / warn / mask / redact) for enterprise environments.
  • Benchmark Korean sensitive-entity extraction for PII + secret/token patterns.

Not Intended Use

  • Re-identification, deanonymization, or tracking of real individuals.
  • Assuming real-world distributions (this is synthetic data and may differ from production traffic).

Data Format

  • Primary format: JSON / JSONL (chat-style SFT samples)
  • Columns
    • id (int): sample identifier
    • messages (list): chat messages in SFT style, typically 3 turns:
      • system: instruction to act as a strict whitelist-only detector
      • user: input text
      • assistant: target JSON output (no extra text)

Output Contract (Assistant Message)

The assistant content is a JSON string and follows this schema:

{
  "text": "<original input text verbatim>",
  "has_sensitive": <boolean>,
  "entities": [
    {
      "value": "<exact substring as it appears in the text>",
      "begin": <integer>,   // 0-based char offset (inclusive)
      "end": <integer>,     // 0-based char offset (exclusive)
      "label": "<UPPER_SNAKE_CASE category>"
    }
  ]
}

Whitelist Label Set (Allowed Labels)

Models trained on this dataset are expected to only output the following labels:

Basic identity

  • NAME β€” Person name
  • PHONE β€” Phone number
  • EMAIL β€” Email address
  • ADDRESS β€” Address (road name / district / detailed address)
  • POSTAL_CODE β€” Postal/ZIP code

Government / official identifiers

  • PERSONAL_CUSTOMS_ID β€” Personal Customs Clearance Code (KR)
  • RESIDENT_ID β€” Resident Registration Number (KR)
  • PASSPORT β€” Passport number
  • DRIVER_LICENSE β€” Driver’s license number
  • FOREIGNER_ID β€” Foreigner registration number
  • HEALTH_INSURANCE_ID β€” Health insurance ID
  • BUSINESS_ID β€” Business registration number
  • MILITARY_ID β€” Military service number

Authentication / secrets

  • JWT β€” JSON Web Token
  • API_KEY β€” API key (vendor-agnostic)
  • GITHUB_PAT β€” GitHub Personal Access Token
  • PRIVATE_KEY β€” Private key material (SSH/TLS/PGP)

Financial

  • CARD_NUMBER β€” Card number
  • CARD_EXPIRY β€” Card expiry (MM/YY etc.)
  • BANK_ACCOUNT β€” Bank account number
  • CARD_CVV β€” CVC/CVV
  • PAYMENT_PIN β€” Payment/ATM PIN
  • MOBILE_PAYMENT_PIN β€” Mobile payment PIN

Crypto

  • MNEMONIC β€” Recovery seed phrase / mnemonic
  • CRYPTO_PRIVATE_KEY β€” Crypto private key
  • HD_WALLET β€” HD wallet extended key
  • PAYMENT_URI_QR β€” Payment URI / QR payload (BTC/ETH/XRP/SOL/TRON etc.)

Network / device

  • IPV4 β€” IPv4 address
  • IPV6 β€” IPv6 address
  • MAC_ADDRESS β€” MAC address
  • IMEI β€” IMEI

Splits

  • train: ~52.9k rows (v3 release)

Recommendation: If you add validation / test splits later, consider releasing them under a new version (e.g., v4) for reproducibility.

How to Load (Hugging Face Datasets)

from datasets import load_dataset

ds = load_dataset("BoB14TeamSentinel/sentinel-kr-sensitive-entities-synthetic-v3")
print(ds["train"][0])

Quality Notes / Limitations

  • Synthetic generation may not perfectly match real-world traffic (domain shift).
  • Some patterns may be over/under-represented depending on the generation prompts.
  • Ambiguous numeric strings may cause false positives in some settings.

Safety & Ethics

  • This dataset was created to reduce privacy risk by using synthetic data only.
  • Do not use it for real-person identification or any privacy-invasive purpose.

License

This dataset is released under CC BY 4.0.
You must provide appropriate attribution when using or redistributing it.

Citation / Attribution

If you use this dataset, please attribute:

  • BoB14TeamSentinel, Sentinel KR Sensitive Entities (Synthetic) v3 (Hugging Face dataset)

Project

  • Project: Sentinel Solution
  • Organization: Team.될것같은데
Downloads last month
21