Dataset Viewer
Auto-converted to Parquet Duplicate
triple1
listlengths
3
3
triple2
listlengths
3
3
triple3
listlengths
3
3
triple1_labels
listlengths
3
3
triple2_labels
listlengths
3
3
triple3_labels
listlengths
3
3
description
stringlengths
8
19
keep_triple
bool
1 class
query_prompt
stringlengths
3.23k
3.36k
query
stringlengths
85
226
entity_a
stringlengths
3
55
entity_b
stringlengths
4
85
rel_b
stringclasses
88 values
index
int64
0
930
prompt
listlengths
3
3
path_prediction
listlengths
1
1
prompt_for_path
listlengths
1
1
all_response_tokens
listlengths
1
1
all_reasoning_tokens
listlengths
1
1
response_1
stringlengths
1.98k
8.69k
parsed_paths
stringlengths
4
12.2k
iterate_prompt_1
listlengths
3
3
path_prediction_old_{counter}
listlengths
1
1
prompt_for_path_old_{counter}
listlengths
1
1
usage
listlengths
1
1
raw_path_prediction
listlengths
1
1
source_path
listlengths
3
3
reasoning_paths
listlengths
1
1
paths_0
stringlengths
2
12.2k
reasoning_0
stringlengths
790
13.7k
relation_recall_scores_set_0
float64
0
0
num_paths_where_source_relations_found_0
float64
0
0
path_recall_scores_set_0
float64
0
0
num_paths_where_source_triple_found_0
float64
0
0
relation_lexical_uniqueness_0
int64
0
88
entity_lexical_uniqueness_0
int64
0
208
num_triples_0
int64
0
216
uniqueness_scores_0
listlengths
1
80
unique_raw_response_0
listlengths
1
80
max_uniqueness_score_0
listlengths
1
80
factuality_scores_0
listlengths
1
80
raw_responses_factuality_0
listlengths
1
80
parsed_scores_factuality_0
listlengths
1
80
raw_salience_scores_0
listlengths
1
80
min_salience_scores_0
listlengths
1
80
salience_raw_responses_0
listlengths
1
80
validity_per_path_0
listlengths
1
80
validity_reasons_0
listlengths
1
80
avg_path_length_0
float64
0
11.8
num_paths_0
float64
0
80
[ "Q1352656", "P166", "Q935843" ]
[ "Q356715", "P166", "Q935843" ]
[ "Q356715", "P358", "Q100871850" ]
[ "Morton Gould", "award received", "Grammy Lifetime Achievement Award" ]
[ "Benny Carter", "award received", "Grammy Lifetime Achievement Award" ]
[ "Benny Carter", "discography", "Benny Carter discography" ]
Q935843__P166
false
"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)
"What are different ways of connecting Morton Gould, the American composer and conductor, and someon(...TRUNCATED)
Morton Gould
Benny Carter discography
discography
0
[{"content":"Query: What are different ways of connecting Morton Gould, the American composer and co(...TRUNCATED)
["<think>The user is asking me to find connection paths from Morton Gould to someone with a notable (...TRUNCATED)
[[{"content":"Query: What are different ways of connecting Morton Gould, the American composer and c(...TRUNCATED)
[ 2037 ]
[ null ]
"<think>\nLet me analyze this query carefully. I need to find connection paths from \"Morton Gould\"(...TRUNCATED)
"[[[[\"morton gould\", \"recorded for\", \"rca records\"], [\"rca records\", \"recorded\", \"benny c(...TRUNCATED)
[{"content":"Query: What are different ways of connecting Morton Gould, the American composer and co(...TRUNCATED)
["<think>\nLet me analyze this query carefully. I need to find connection paths from \"Morton Gould\(...TRUNCATED)
["Query: What are different ways of connecting Morton Gould, the American composer and conductor, an(...TRUNCATED)
[ { "completion_tokens": 4235, "prompt_tokens": 2388, "total_tokens": 6623 } ]
["<think>The user is asking me to find connection paths from Morton Gould to someone with a notable (...TRUNCATED)
[["Morton Gould","award received","Grammy Lifetime Achievement Award"],["Benny Carter","award receiv(...TRUNCATED)
["<think>The user is asking me to find connection paths from Morton Gould to someone with a notable (...TRUNCATED)
"[[[\"morton gould\", \"recorded for\", \"rca records\"], [\"rca records\", \"recorded\", \"benny ca(...TRUNCATED)
"\"<think>The user is asking me to find connection paths from Morton Gould to someone with a notable(...TRUNCATED)
0
0
0
0
30
36
70
[[1,1,1],[1,1,1],[2,1,1],[2,1,1],[2,1,1],[1,1,1],[1,2,1],[1,1,1],[1,1,1],[1,1,1],[1,1,1],[1,1,1],[1,(...TRUNCATED)
["{\n \"explanation\": \"Morton Gould is publicly known as a composer and conductor; recording for (...TRUNCATED)
[ 1, 1, 2, 2, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1, 2, 2, 1, 2, 3, 1, 1, 2, 1, 1, 1, 1, 3, 2, 2 ]
[1.0,0.0,1.0,0.0,1.0,1.0,1.0,1.0,1.0,1.0,0.0,1.0,1.0,1.0,0.0,1.0,1.0,0.0,1.0,1.0,1.0,0.0,1.0,1.0,0.0(...TRUNCATED)
["{\n \"explanation\": \"All three triples involve real, identifiable entities and plausible relati(...TRUNCATED)
[[1.0,1.0,1.0],[1.0,1.0,0.0],[1.0,1.0,1.0],[1.0,0.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0],[(...TRUNCATED)
[[2,2,5],[3,1,5],[3,3,5],[1,4,5],[2,2,5],[5,4,5],[2,1,5],[3,1,5],[1,1,5],[1,1,4],[2,2,5],[2,1,5],[1,(...TRUNCATED)
[2.0,1.0,3.0,1.0,2.0,4.0,1.0,1.0,1.0,1.0,2.0,1.0,1.0,2.0,1.0,3.0,2.0,4.0,1.0,1.0,4.0,2.0,1.0,1.0,1.0(...TRUNCATED)
["[\n {\n \"explanation\": \"Class A (subjects that recorded for RCA Records): RCA is a historic(...TRUNCATED)
[1.0,1.0,1.0,1.0,1.0,1.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,1.0,1.0,1.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0(...TRUNCATED)
["","","","","","","triple 0 is not length three","","","triple 0 is not length three","triple 0 is (...TRUNCATED)
3
35
[ "Q57067", "P166", "Q38104" ]
[ "Q131729", "P166", "Q38104" ]
[ "Q131729", "P106", "Q593644" ]
[ "Max von Laue", "award received", "Nobel Prize in Physics" ]
[ "William Lawrence Bragg", "award received", "Nobel Prize in Physics" ]
[ "William Lawrence Bragg", "occupation", "chemist" ]
Q38104__P166
false
"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)
"What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffr(...TRUNCATED)
Max von Laue
chemist
occupation
1
[{"content":"Query: What are different ways of connecting Max von Laue, the physicist known for his (...TRUNCATED)
["<think>The user is asking for more and different connections between Max von Laue (physicist) and (...TRUNCATED)
[[{"content":"Query: What are different ways of connecting Max von Laue, the physicist known for his(...TRUNCATED)
[ 2514 ]
[ null ]
"<think>\nLet me think about Max von Laue and how he might connect to chemists.\n\nMax von Laue was (...TRUNCATED)
"[[[[\"max von laue\", \"worked at\", \"kaiser wilhelm institute\"], [\"kaiser wilhelm institute\", (...TRUNCATED)
[{"content":"Query: What are different ways of connecting Max von Laue, the physicist known for his (...TRUNCATED)
["<think>\nLet me think about Max von Laue and how he might connect to chemists.\n\nMax von Laue was(...TRUNCATED)
["Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-r(...TRUNCATED)
[ { "completion_tokens": 2190, "prompt_tokens": 1952, "total_tokens": 4142 } ]
["<think>The user is asking for more and different connections between Max von Laue (physicist) and (...TRUNCATED)
[["Max von Laue","award received","Nobel Prize in Physics"],["William Lawrence Bragg","award receive(...TRUNCATED)
["<think>The user is asking for more and different connections between Max von Laue (physicist) and (...TRUNCATED)
"[[[\"max von laue\", \"worked at\", \"kaiser wilhelm institute\"], [\"kaiser wilhelm institute\", \(...TRUNCATED)
"\"<think>The user is asking for more and different connections between Max von Laue (physicist) and(...TRUNCATED)
0
0
0
0
54
44
65
[[1,1,1],[1,1,1],[1,1,1],[1,2,1],[1,2,1],[1,2,1,1],[1,1,1],[1,1,1],[1,1,1],[2,2,1],[2,1,2,3,1],[1,1,(...TRUNCATED)
["{\n \"explanation\": \"Max von Laue is publicly known as a Nobel‑winning physicist; his employm(...TRUNCATED)
[ 1, 1, 1, 2, 2, 2, 1, 1, 1, 2, 3, 1, 2, 2, 1, 2, 1, 1, 2, 1, 3, 1, 2, 1, 3 ]
[1.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0,1.0(...TRUNCATED)
["{\n \"explanation\": \"All three triples involve real, identifiable historical figures and instit(...TRUNCATED)
[[1.0,1.0,1.0],[1.0,1.0,1.0],[0.0,0.0,1.0],[0.0,1.0,1.0],[1.0,0.0,1.0],[1.0,0.0,1.0,1.0],[1.0,1.0,1.(...TRUNCATED)
[[2,2,1],[5,1,1],[4,4,1],[4,3,1],[1,3,1],[3,4,3,1],[5,4,1],[1,1,1],[2,3,1],[1,1,1],[5,4,5,3,1],[1,4,(...TRUNCATED)
[2.0,1.0,4.0,3.0,1.0,3.0,4.0,1.0,2.0,1.0,3.0,1.0,3.0,1.0,4.0,1.0,4.0,2.0,3.0,3.0,1.0,1.0,4.0,1.0,1.0(...TRUNCATED)
["[\n {\n \"explanation\": \"Class A (subjects who worked at the Kaiser Wilhelm Institute): the (...TRUNCATED)
[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0(...TRUNCATED)
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
3.6
25
[ "Q2085", "P161", "Q164328" ]
[ "Q2085", "P161", "Q174263" ]
[ "Q174263", "P19", "Q268873" ]
[ "Twin Peaks", "cast member", "David Koechner" ]
[ "Twin Peaks", "cast member", "Rodney Rowland" ]
[ "Rodney Rowland", "place of birth", "Newport Beach" ]
Q2085__P161
false
"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)
"What are different ways of connecting David Koechner, the American actor and comedian, and someone (...TRUNCATED)
David Koechner
Newport Beach
place of birth
2
[{"content":"Query: What are different ways of connecting David Koechner, the American actor and com(...TRUNCATED)
["<think>The user is asking me to find connections between David Koechner (actor/comedian) and someo(...TRUNCATED)
[[{"content":"Query: What are different ways of connecting David Koechner, the American actor and co(...TRUNCATED)
[ 1844 ]
[ 0 ]
"<think>I need to find connection paths from David Koechner (American actor and comedian) to someone(...TRUNCATED)
"[[[[\"david koechner\", \"appeared in\", \"anchorman\"], [\"anchorman\", \"directed by\", \"adam mc(...TRUNCATED)
[{"content":"Query: What are different ways of connecting David Koechner, the American actor and com(...TRUNCATED)
["<think>I need to find connection paths from David Koechner (American actor and comedian) to someon(...TRUNCATED)
["Query: What are different ways of connecting David Koechner, the American actor and comedian, and (...TRUNCATED)
[ { "completion_tokens": 2248, "prompt_tokens": 1961, "total_tokens": 4209 } ]
["<think>The user is asking me to find connections between David Koechner (actor/comedian) and someo(...TRUNCATED)
[["Twin Peaks","cast member","David Koechner"],["Twin Peaks","cast member","Rodney Rowland"],["Rodne(...TRUNCATED)
["<think>The user is asking me to find connections between David Koechner (actor/comedian) and someo(...TRUNCATED)
"[[[\"david koechner\", \"appeared in\", \"anchorman\"], [\"anchorman\", \"directed by\", \"adam mck(...TRUNCATED)
"\"<think>The user is asking me to find connections between David Koechner (actor/comedian) and some(...TRUNCATED)
0
0
0
0
60
71
93
[[1,1,1,3,2,2],[1,1,2,2,1,1,1,3,2,2],[3,1,1,1,2,1],[1,1,2,2,2,2],[1,1,1,2,2,1,2,1],[1,1,2,2,1,2,1],[(...TRUNCATED)
["{\n \"explanation\": \"1. David Koechner is publicly known as an actor/comedian, and the fact tha(...TRUNCATED)
[ 3, 3, 3, 2, 2, 2, 2, 2, 1, 2, 2, 3, 3, 2, 2 ]
[ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ]
["{\n \"explanation\": \"The first two triples are correct: David Koechner did appear in the film A(...TRUNCATED)
[[1.0,1.0,0.0,0.0,0.0,0.0],[0.0,0.0,0.0,0.0,1.0,0.0,1.0,0.0,0.0,0.0],[0.0,1.0,0.0,0.0,0.0,0.0],[1.0,(...TRUNCATED)
[[4,4,1,1,1,2],[3,5,5,2,3,4,4,4,4,3],[3,1,2,3,5,2],[1,1,1,4,4,1],[4,2,2,2,1,2,1,2],[3,2,3,4,2,3,3],[(...TRUNCATED)
[ 1, 2, 1, 1, 1, 2, 1, 4, 1, 1, 2, 1, 1, 1, 1 ]
["[\n {\n \"explanation\": \"Class A (subjects that appeared in Anchorman) includes the cast and(...TRUNCATED)
[ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
7.2
15
[ "Q18037479", "P2293", "Q11081" ]
[ "Q18053558", "P2293", "Q11081" ]
[ "Q18053558", "P2548", "Q22809711" ]
[ "CD2AP", "genetic association", "Alzheimer's disease" ]
[ "ATXN7L1", "genetic association", "Alzheimer's disease" ]
[ "ATXN7L1", "strand orientation", "reverse strand" ]
Q11081__P2293
false
"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)
"What are different ways of connecting CD2AP, a protein involved in cellular processes, and a substa(...TRUNCATED)
CD2AP
reverse strand
strand orientation
3
[{"content":"Query: What are different ways of connecting CD2AP, a protein involved in cellular proc(...TRUNCATED)
["<think>The user is asking me to expand the paths significantly and even says \"Don't worry too muc(...TRUNCATED)
[[{"content":"Query: What are different ways of connecting CD2AP, a protein involved in cellular pro(...TRUNCATED)
[ 2142 ]
[ null ]
"<think>\nLet me analyze this query carefully:\n\n1. Start entity: CD2AP (a protein involved in cell(...TRUNCATED)
"[[[[\"cd2ap\", \"encoded by\", \"cd2ap gene\"], [\"cd2ap gene\", \"strand orientation\", \"reverse (...TRUNCATED)
[{"content":"Query: What are different ways of connecting CD2AP, a protein involved in cellular proc(...TRUNCATED)
["<think>\nLet me analyze this query carefully:\n\n1. Start entity: CD2AP (a protein involved in cel(...TRUNCATED)
["Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and (...TRUNCATED)
[ { "completion_tokens": 3830, "prompt_tokens": 2609, "total_tokens": 6439 } ]
["<think>The user is asking me to expand the paths significantly and even says \"Don't worry too muc(...TRUNCATED)
[["CD2AP","genetic association","Alzheimer's disease"],["ATXN7L1","genetic association","Alzheimer's(...TRUNCATED)
["<think>The user is asking me to expand the paths significantly and even says \"Don't worry too muc(...TRUNCATED)
"[[[\"cd2ap\", \"encoded by\", \"cd2ap gene\"], [\"cd2ap gene\", \"strand orientation\", \"reverse s(...TRUNCATED)
"\"<think>The user is asking me to expand the paths significantly and even says \\\"Don't worry too (...TRUNCATED)
0
0
0
0
69
113
116
[[1,1],[1,1,3],[2,3,3],[1,1,1,3],[1,1,1,3],[1,1,1,3],[1,1,1,1,2],[1,1,1,2,3],[1,1,1,1,1],[1,1,1,1,1](...TRUNCATED)
["{\n \"explanation\": \"The subject 'cd2ap' is a protein (CD2-associated protein), whose core publ(...TRUNCATED)
[ 1, 1, 3, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 2, 3, 1, 1, 2, 1, 1, 1, 1, 1 ]
[0.0,1.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,1.0,1.0,1.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0(...TRUNCATED)
["{\n \"explanation\": \"The first triple links the protein CD2AP (written as \\\"cd2ap\\\") to the(...TRUNCATED)
[[1.0,0.0],[1.0,1.0,1.0],[1.0,1.0,0.0],[1.0,1.0,1.0,0.0],[1.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.(...TRUNCATED)
[[5,1],[4,5,1],[1,1,1],[3,4,5,1],[3,4,5,1],[4,4,5,1],[4,3,4,5,1],[1,2,2,1,1],[3,4,5,5,1],[1,1,3,5,1](...TRUNCATED)
[5.0,4.0,1.0,3.0,3.0,4.0,3.0,1.0,3.0,1.0,3.0,4.0,1.0,3.0,4.0,3.0,4.0,1.0,4.0,1.0,1.0,3.0,1.0,1.0,1.0(...TRUNCATED)
["[\n {\n \"explanation\": \"Class A (subject‑variation): all subjects that are encoded by the(...TRUNCATED)
[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0(...TRUNCATED)
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
4.866667
30
[ "Q283572", "P463", "Q254138" ]
[ "Q316136", "P463", "Q254138" ]
[ "Q316136", "P19", "Q39709" ]
[ "Kun Nong", "member of", "Slipknot" ]
[ "Chris Fehn", "member of", "Slipknot" ]
[ "Chris Fehn", "place of birth", "Des Moines" ]
Q254138__P463
false
"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)
What are different ways of connecting Kun Nong and someone who was born in Des Moines?
Kun Nong
Des Moines
place of birth
4
[{"content":"Query: What are different ways of connecting Kun Nong and someone who was born in Des M(...TRUNCATED)
["<think>The user is asking me to find connection paths from \"Kun Nong\" to someone who was born in(...TRUNCATED)
[[{"content":"Query: What are different ways of connecting Kun Nong and someone who was born in Des (...TRUNCATED)
[ 946 ]
[ 0 ]
"<think>Let me think about who Kun Nong is and potential connections to someone born in Des Moines.\(...TRUNCATED)
"[[[[\"kun nong\", \"worked with\", \"ashton kutcher\"], [\"ashton kutcher\", \"place of birth\", \"(...TRUNCATED)
[{"content":"Query: What are different ways of connecting Kun Nong and someone who was born in Des M(...TRUNCATED)
["<think>Let me think about who Kun Nong is and potential connections to someone born in Des Moines.(...TRUNCATED)
["Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines?\n\nT(...TRUNCATED)
[ { "completion_tokens": 940, "prompt_tokens": 1174, "total_tokens": 2114 } ]
["<think>The user is asking me to find connection paths from \"Kun Nong\" to someone who was born in(...TRUNCATED)
[["Kun Nong","member of","Slipknot"],["Chris Fehn","member of","Slipknot"],["Chris Fehn","place of b(...TRUNCATED)
["<think>The user is asking me to find connection paths from \"Kun Nong\" to someone who was born in(...TRUNCATED)
"[[[\"kun nong\", \"worked with\", \"ashton kutcher\"], [\"ashton kutcher\", \"place of birth\", \"d(...TRUNCATED)
"\"<think>The user is asking me to find connection paths from \\\"Kun Nong\\\" to someone who was bo(...TRUNCATED)
0
0
0
0
15
13
15
[ [ 3, 2 ], [ 3, 2 ], [ 2, 2 ], [ 1, 2 ], [ 1, 2 ], [ 3, 2 ], [ 3, 1, 1, 1 ], [ 3, 1, 1 ], [ 3, 1, 2 ], [ 2, 1, 2 ] ]
["{\n \"explanation\": \"The subject Kun Nong is a legendary Chinese culture hero; his core public (...TRUNCATED)
[ 3, 3, 2, 1, 1, 3, 3, 3, 3, 2 ]
[ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ]
["{\n \"explanation\": \"The first triple claims that \\\"kun nong\\\" worked with Ashton Kutcher. (...TRUNCATED)
[[0.0,0.0],[0.0,0.0],[0.0,1.0],[0.0,0.0],[0.0,0.0],[0.0,0.0],[0.0,1.0,1.0,0.0],[0.0,1.0,0.0],[0.0,0.(...TRUNCATED)
[ [ 3, 1 ], [ 3, 1 ], [ 3, 3 ], [ 3, 1 ], [ 4, 1 ], [ 1, 1 ], [ 2, 1, 3, 1 ], [ 3, 1, 2 ], [ 5, 4, 1 ], [ 1, 1, 3 ] ]
[ 3, 3, 3, 3, 4, 1, 1, 1, 4, 1 ]
["[\n {\n \"explanation\": \"Class A (subjects who worked with Ashton Kutcher): Ashton Kutcher i(...TRUNCATED)
[ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ]
[ "", "", "", "", "", "", "", "", "", "" ]
2.5
10
[ "Q423327", "P2175", "Q12199" ]
[ "Q422654", "P2175", "Q12199" ]
[ "Q422654", "P769", "Q898407" ]
[ "enfuvirtide", "medical condition treated", "HIV/AIDS" ]
[ "saquinavir", "medical condition treated", "HIV/AIDS" ]
[ "saquinavir", "significant drug interaction", "venlafaxine" ]
Q12199__P2175
false
"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)
"What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a substance (...TRUNCATED)
enfuvirtide
venlafaxine
significant drug interaction
5
[{"content":"Query: What are different ways of connecting enfuvirtide, a medication used to treat HI(...TRUNCATED)
["<think>The user is asking me to find MORE diverse connection paths from enfuvirtide to substances (...TRUNCATED)
[[{"content":"Query: What are different ways of connecting enfuvirtide, a medication used to treat H(...TRUNCATED)
[ 2262 ]
[ null ]
"<think>\nLet me analyze this query systematically.\n\nThe query asks for connection paths from:\n- (...TRUNCATED)
"[[[[\"enfuvirtide\", \"class\", \"entry inhibitors\"], [\"entry inhibitors\", \"combined with\", \"(...TRUNCATED)
[{"content":"Query: What are different ways of connecting enfuvirtide, a medication used to treat HI(...TRUNCATED)
["<think>\nLet me analyze this query systematically.\n\nThe query asks for connection paths from:\n-(...TRUNCATED)
["Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a su(...TRUNCATED)
[ { "completion_tokens": 3663, "prompt_tokens": 2768, "total_tokens": 6431 } ]
["<think>The user is asking me to find MORE diverse connection paths from enfuvirtide to substances (...TRUNCATED)
[["enfuvirtide","medical condition treated","HIV/AIDS"],["saquinavir","medical condition treated","H(...TRUNCATED)
["<think>The user is asking me to find MORE diverse connection paths from enfuvirtide to substances (...TRUNCATED)
"[[[\"enfuvirtide\", \"class\", \"entry inhibitors\"], [\"entry inhibitors\", \"combined with\", \"p(...TRUNCATED)
"\"<think>The user is asking me to find MORE diverse connection paths from enfuvirtide to substances(...TRUNCATED)
0
0
0
0
67
64
85
[[1,2,1,3],[1,1,1,2],[1,1,2,1],[1,2,1,1,1],[1,1,2,2],[1,1,1,1],[1,1,1,1,1,1],[1,2,1,2],[1,2,1,3,2],[(...TRUNCATED)
["{\n \"explanation\": \"Enfuvirtide is primarily known as an HIV antiretroviral drug (a fusion/ent(...TRUNCATED)
[ 2, 1, 2, 2, 2, 1, 1, 2, 3, 1, 2, 2, 2, 2, 2, 1, 2, 2, 3, 1, 1, 2, 2, 1, 2 ]
[0.0,1.0,1.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0(...TRUNCATED)
["{\n \"explanation\": \"The first triple correctly states that enfuvirtide is a member of the drug(...TRUNCATED)
[[1.0,1.0,1.0,0.0],[1.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[0.0,1.0,1.0,1.0,1.0],[0.0,1.0,1.0,0.0],[1.0,(...TRUNCATED)
[[5,4,4,4],[4,5,4,4],[4,4,4,4],[4,3,4,4,4],[2,2,3,3],[4,4,4,4],[5,5,4,5,5,4],[4,4,4,4],[5,1,2,4,4],[(...TRUNCATED)
[4.0,4.0,4.0,3.0,2.0,4.0,4.0,4.0,1.0,1.0,1.0,3.0,1.0,3.0,4.0,4.0,4.0,4.0,2.0,3.0,4.0,3.0,3.0,4.0,3.0(...TRUNCATED)
["[\n {\n \"explanation\": \"Class A (subjects that are entry inhibitors): known entry inhibitor(...TRUNCATED)
[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0(...TRUNCATED)
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
4.4
25
[ "Q77462", "P463", "Q32645" ]
[ "Q95556", "P463", "Q32645" ]
[ "Q95556", "P451", "Q551050" ]
[ "Bela B", "member of", "Die Ärzte" ]
[ "Hagen Liebing", "member of", "Die Ärzte" ]
[ "Hagen Liebing", "unmarried partner", "Anja Caspary" ]
Q32645__P463
false
"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)
"What are different ways of connecting Bela B, the German musician, and someone who is the unmarried(...TRUNCATED)
Bela B
Anja Caspary
unmarried partner
6
[{"content":"Query: What are different ways of connecting Bela B, the German musician, and someone w(...TRUNCATED)
["<think>The user is asking me to find connection paths between Bela B (German musician) and Anja Ca(...TRUNCATED)
[[{"content":"Query: What are different ways of connecting Bela B, the German musician, and someone (...TRUNCATED)
[ 1302 ]
[ 0 ]
"<think>Let me analyze this query step by step.\n\nI need to find connection paths from \"Bela B\" ((...TRUNCATED)
"[[[[\"bela b\", \"member of band\", \"die \\u00e4rzte\"], [\"die \\u00e4rzte\", \"collaborated with(...TRUNCATED)
[{"content":"Query: What are different ways of connecting Bela B, the German musician, and someone w(...TRUNCATED)
["<think>Let me analyze this query step by step.\n\nI need to find connection paths from \"Bela B\" (...TRUNCATED)
["Query: What are different ways of connecting Bela B, the German musician, and someone who is the u(...TRUNCATED)
[ { "completion_tokens": 1580, "prompt_tokens": 1607, "total_tokens": 3187 } ]
["<think>The user is asking me to find connection paths between Bela B (German musician) and Anja Ca(...TRUNCATED)
[["Bela B","member of","Die Ärzte"],["Hagen Liebing","member of","Die Ärzte"],["Hagen Liebing","un(...TRUNCATED)
["<think>The user is asking me to find connection paths between Bela B (German musician) and Anja Ca(...TRUNCATED)
"[[[\"bela b\", \"member of band\", \"die \\u00e4rzte\"], [\"die \\u00e4rzte\", \"collaborated with (...TRUNCATED)
"\"<think>The user is asking me to find connection paths between Bela B (German musician) and Anja C(...TRUNCATED)
0
0
0
0
31
16
31
[[1,2,3],[1,1,3],[1,1,2],[1,1,3],[1,2,3],[1,1,3],[1,1,3],[1,1,3],[2,1,3],[1,1,2],[1,1,3],[1,1,1,3],[(...TRUNCATED)
["{\n \"explanation\": \"Bela B is best known as a musician and drummer for the German punk band Di(...TRUNCATED)
[ 2, 1, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 1, 2, 1 ]
[ 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0 ]
["{\n \"explanation\": \"The first triple is correct: Bela B (real German musician) is indeed a mem(...TRUNCATED)
[[1.0,1.0,0.0],[1.0,1.0,0.0],[1.0,0.0,0.0],[0.0,0.0,1.0],[1.0,1.0,0.0],[1.0,1.0,0.0],[1.0,1.0,0.0],[(...TRUNCATED)
[[5,4,5],[3,3,5],[4,4,5],[4,4,5],[1,1,5],[3,3,5],[3,3,5],[2,2,5],[5,4,5],[2,3,5],[1,1,5],[4,4,4,5],[(...TRUNCATED)
[ 4, 3, 4, 4, 1, 3, 3, 2, 4, 2, 1, 4, 2, 1, 1 ]
["[\n {\n \"explanation\": \"Class A (subjects that are members of the band Die Ärzte): histori(...TRUNCATED)
[ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
3.066667
15
[ "Q651253", "P40", "Q1268" ]
[ "Q9356382", "P40", "Q1268" ]
[ "Q9356382", "P22", "Q11716498" ]
[ "Nicolas Chopin", "child", "Frédéric Chopin" ]
[ "Tekla Justyna Chopin", "child", "Frédéric Chopin" ]
[ "Tekla Justyna Chopin", "father", "Jakub Krzyżanowski" ]
Q1268__P40
false
"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)
"What are different ways of connecting Nicolas Chopin, and someone who is the father of Jakub Krzyż(...TRUNCATED)
Nicolas Chopin
Jakub Krzyżanowski
father
7
[{"content":"Query: What are different ways of connecting Nicolas Chopin, and someone who is the fat(...TRUNCATED)
["<think>The user is asking me to find connection paths from Nicolas Chopin to someone who is the fa(...TRUNCATED)
[[{"content":"Query: What are different ways of connecting Nicolas Chopin, and someone who is the fa(...TRUNCATED)
[ 989 ]
[ 0 ]
"<think>Let me think about this query. I need to find connection paths from \"Nicolas Chopin\" to so(...TRUNCATED)
"[[[[\"nicolas chopin\", \"father of\", \"fr\\u00e9d\\u00e9ric chopin\"], [\"fr\\u00e9d\\u00e9ric ch(...TRUNCATED)
[{"content":"Query: What are different ways of connecting Nicolas Chopin, and someone who is the fat(...TRUNCATED)
["<think>Let me think about this query. I need to find connection paths from \"Nicolas Chopin\" to s(...TRUNCATED)
["Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jaku(...TRUNCATED)
[ { "completion_tokens": 1174, "prompt_tokens": 1351, "total_tokens": 2525 } ]
["<think>The user is asking me to find connection paths from Nicolas Chopin to someone who is the fa(...TRUNCATED)
[["Nicolas Chopin","child","Frédéric Chopin"],["Tekla Justyna Chopin","child","Frédéric Chopin"](...TRUNCATED)
["<think>The user is asking me to find connection paths from Nicolas Chopin to someone who is the fa(...TRUNCATED)
"[[[\"nicolas chopin\", \"father of\", \"fr\\u00e9d\\u00e9ric chopin\"], [\"fr\\u00e9d\\u00e9ric cho(...TRUNCATED)
"\"<think>The user is asking me to find connection paths from Nicolas Chopin to someone who is the f(...TRUNCATED)
0
0
0
0
16
16
19
[ [ 1, 2, 3 ], [ 1, 3, 1 ], [ 2, 1, 3 ], [ 2, 1, 1 ], [ 2, 3 ], [ 1, 1, 3 ], [ 1, 2, 3 ], [ 2, 3, 3 ], [ 1, 1, 3 ], [ 2, 3, 3 ] ]
["{\n \"explanation\": \"The first triple concerns Nicolas Chopin and states that he is the father (...TRUNCATED)
[ 2, 3, 2, 2, 2, 1, 2, 3, 1, 3 ]
[ 0, 0, 0, 0, 0, 0, 1, 0, 0, 0 ]
["{\n \"explanation\": \"The first triple correctly identifies Nicolas (Mikołaj) Chopin as the fat(...TRUNCATED)
[[1.0,1.0,0.0],[1.0,1.0,0.0],[1.0,0.0,0.0],[1.0,1.0,0.0],[1.0,0.0],[1.0,0.0,0.0],[1.0,1.0,1.0],[1.0,(...TRUNCATED)
[ [ 5, 2, 2 ], [ 1, 1, 5 ], [ 1, 1, 1 ], [ 1, 3, 4 ], [ 1, 1 ], [ 1, 4, 3 ], [ 5, 3, 3 ], [ 1, 3, 5 ], [ 5, 3, 3 ], [ 3, 3, 5 ] ]
[ 2, 1, 1, 1, 1, 1, 3, 1, 3, 3 ]
["[\n {\n \"explanation\": \"Class A (subjects that are father of Frédéric Chopin) includes on(...TRUNCATED)
[ 1, 0, 1, 1, 1, 1, 1, 1, 1, 1 ]
[ "", "there is no continuity for the pair (1, 2)", "", "", "", "", "", "", "", "" ]
2.9
10
[ "Q23505", "P40", "Q207" ]
[ "Q190628", "P40", "Q207" ]
[ "Q190628", "P39", "Q7166256" ]
[ "George H. W. Bush", "child", "George W. Bush" ]
[ "Barbara Bush", "child", "George W. Bush" ]
[ "Barbara Bush", "position held", "First Lady of the United States" ]
Q207__P40
false
"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)
"What are different ways of connecting George H. W. Bush, the 41st President of the United States, a(...TRUNCATED)
George H. W. Bush
First Lady of the United States
position held
8
[{"content":"Query: What are different ways of connecting George H. W. Bush, the 41st President of t(...TRUNCATED)
["<think>The user wants me to find many different paths connecting George H. W. Bush to someone who (...TRUNCATED)
[[{"content":"Query: What are different ways of connecting George H. W. Bush, the 41st President of (...TRUNCATED)
[ 1619 ]
[ null ]
"<think>\nLet me think about how to connect George H. W. Bush (41st President) to someone who held t(...TRUNCATED)
"[[[[\"george h. w. bush\", \"spouse\", \"barbara bush\"], [\"barbara bush\", \"position held\", \"f(...TRUNCATED)
[{"content":"Query: What are different ways of connecting George H. W. Bush, the 41st President of t(...TRUNCATED)
["<think>\nLet me think about how to connect George H. W. Bush (41st President) to someone who held (...TRUNCATED)
["Query: What are different ways of connecting George H. W. Bush, the 41st President of the United S(...TRUNCATED)
[ { "completion_tokens": 1494, "prompt_tokens": 1269, "total_tokens": 2763 } ]
["<think>The user wants me to find many different paths connecting George H. W. Bush to someone who (...TRUNCATED)
[["George H. W. Bush","child","George W. Bush"],["Barbara Bush","child","George W. Bush"],["Barbara (...TRUNCATED)
["<think>The user wants me to find many different paths connecting George H. W. Bush to someone who (...TRUNCATED)
"[[[\"george h. w. bush\", \"spouse\", \"barbara bush\"], [\"barbara bush\", \"position held\", \"fi(...TRUNCATED)
"\"<think>The user wants me to find many different paths connecting George H. W. Bush to someone who(...TRUNCATED)
0
0
0
0
17
10
24
[ [ 2, 1 ], [ 2, 2, 1 ], [ 1, 2, 1 ], [ 2, 1, 2, 1 ], [ 1, 1, 2, 1 ], [ 1, 2, 1 ], [ 2, 1, 2, 1 ], [ 2, 3, 1, 2, 1 ], [ 1, 1, 1 ], [ 1, 1, 1 ] ]
["{\n \"explanation\": \"George H. W. Bush is primarily known as a U.S. President and politician. T(...TRUNCATED)
[ 2, 2, 2, 2, 2, 2, 2, 3, 1, 1 ]
[ 1, 0, 1, 1, 1, 1, 1, 1, 1, 0 ]
["{\n \"explanation\": \"Both triples involve real, well‑known individuals. George H. W. Bush was(...TRUNCATED)
[[1.0,1.0],[0.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.(...TRUNCATED)
[ [ 5, 4 ], [ 5, 5, 4 ], [ 5, 5, 4 ], [ 1, 1, 5, 4 ], [ 1, 1, 5, 4 ], [ 4, 4, 4 ], [ 5, 4, 4, 4 ], [ 1, 1, 5, 5, 4 ], [ 2, 5, 4 ], [ 5, 5, 4 ] ]
[ 5, 5, 5, 1, 1, 4, 4, 1, 2, 5 ]
["[\n {\n \"explanation\": \"Class A (subjects that could be spouse of Barbara Bush): historical(...TRUNCATED)
[ 1, 1, 1, 1, 1, 1, 1, 0, 1, 1 ]
[ "", "", "", "", "", "", "", "there is no continuity for the pair (3, 4)", "", "" ]
3.4
10
[ "Q18037778", "P2293", "Q131755" ]
[ "Q18046338", "P2293", "Q131755" ]
[ "Q18046338", "P5572", "Q64386" ]
[ "INTS7", "genetic association", "bipolar disorder" ]
[ "MCTP1", "genetic association", "bipolar disorder" ]
[ "MCTP1", "expressed in", "gallbladder" ]
Q131755__P2293
false
"Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED)
"What are different ways of connecting INTS7, a protein involved in various cellular processes, and (...TRUNCATED)
INTS7
gallbladder
expressed in
9
[{"content":"Query: What are different ways of connecting INTS7, a protein involved in various cellu(...TRUNCATED)
["<think>The user is asking for more diverse and different paths connecting INTS7 to something expre(...TRUNCATED)
[[{"content":"Query: What are different ways of connecting INTS7, a protein involved in various cell(...TRUNCATED)
[ 1827 ]
[ 0 ]
"<think>Let me break down this task:\n\n1. Start entity: INTS7 (a protein)\n2. End condition: A trip(...TRUNCATED)
"[[[[\"ints7\", \"component of\", \"integrator complex\"], [\"integrator complex\", \"regulates\", \(...TRUNCATED)
[{"content":"Query: What are different ways of connecting INTS7, a protein involved in various cellu(...TRUNCATED)
["<think>Let me break down this task:\n\n1. Start entity: INTS7 (a protein)\n2. End condition: A tri(...TRUNCATED)
["Query: What are different ways of connecting INTS7, a protein involved in various cellular process(...TRUNCATED)
[ { "completion_tokens": 1836, "prompt_tokens": 1971, "total_tokens": 3807 } ]
["<think>The user is asking for more diverse and different paths connecting INTS7 to something expre(...TRUNCATED)
[["INTS7","genetic association","bipolar disorder"],["MCTP1","genetic association","bipolar disorder(...TRUNCATED)
["<think>The user is asking for more diverse and different paths connecting INTS7 to something expre(...TRUNCATED)
"[[[\"ints7\", \"component of\", \"integrator complex\"], [\"integrator complex\", \"regulates\", \"(...TRUNCATED)
"\"<think>The user is asking for more diverse and different paths connecting INTS7 to something expr(...TRUNCATED)
0
0
0
0
34
40
40
[[1,1,2],[1,1,1],[1,2,1],[1,1,1],[1,2,1],[1,1,2],[1,1,2],[1,1,1],[1,1,2],[1,1,1],[1,1,1],[1,1,2],[1,(...TRUNCATED)
["{\n \"explanation\": \"The subject ints7 is a protein subunit of the Integrator complex, so the f(...TRUNCATED)
[ 1, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 3, 1, 2, 1 ]
[ 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0 ]
["{\n \"explanation\": \"The first triple is correct: INTS7 (also known as Integrator complex subun(...TRUNCATED)
[[1.0,0.0,0.0],[1.0,1.0,1.0],[1.0,1.0,0.0],[1.0,1.0,1.0],[1.0,1.0,1.0],[0.0,1.0,1.0],[1.0,0.0,1.0],[(...TRUNCATED)
[[4,3,1],[4,3,1],[4,4,2],[4,1,1],[4,4,3],[4,1,2],[3,1,1],[4,3,2],[4,2,1],[4,1,2],[4,4,3],[4,3,2],[3,(...TRUNCATED)
[ 3, 3, 4, 1, 4, 1, 1, 3, 2, 1, 4, 3, 3, 1, 2, 4, 5, 3, 2, 3 ]
["[\n {\n \"explanation\": \"Class A (subjects that are components of the integrator complex): t(...TRUNCATED)
[ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ]
[ "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "", "" ]
3
20
End of preview. Expand in Data Studio
README.md exists but content is empty.
Downloads last month
7