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 stringlengths 3.53k 3.75k | path_prediction listlengths 1 1 | prompt_for_path listlengths 1 1 | usage listlengths 1 1 | raw_path_prediction listlengths 1 1 | source_path listlengths 3 3 | parsed_paths stringlengths 4 3.41k | reasoning_paths listlengths 1 1 | paths_0 stringlengths 2 3.4k | reasoning_0 stringlengths 4 33.5k | 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 29 | entity_lexical_uniqueness_0 int64 0 52 | num_triples_0 int64 0 53 | uniqueness_scores_0 listlengths 1 19 | unique_raw_response_0 listlengths 1 19 | max_uniqueness_score_0 listlengths 1 19 | factuality_scores_0 listlengths 1 19 | raw_responses_factuality_0 listlengths 1 19 | parsed_scores_factuality_0 listlengths 1 19 | raw_salience_scores_0 listlengths 1 19 | min_salience_scores_0 listlengths 1 19 | salience_raw_responses_0 listlengths 1 19 | validity_per_path_0 listlengths 1 19 | validity_reasons_0 listlengths 1 19 | avg_path_length_0 float64 0 13 | num_paths_0 float64 0 19 | reasoning_trace stringlengths 2.22k 33.8k | len_reasoning_trace int64 2.22k 33.8k | split_reasoning_trace listlengths 1 1 | chunk_index listlengths 1 1 | entities listlengths 0 78 | relations listlengths 0 37 | num_entities int64 0 78 | num_relations int64 0 37 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[
"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.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry? | Morton Gould | Benny Carter discography | discography | 0 | Query: What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relatio... | [
"<think>\nOkay, let's tackle this query. The user wants to connect Morton Gould, the American composer and conductor, to the \"Benny Carter discography\" through multiple distinct paths. Each path must start with Morton Gould and end with a triple where the relationship is 'discography' and the tail is 'Benny Carte... | [
"Query: What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, ... | [
{
"completion_tokens": 2249,
"prompt_tokens": 748,
"total_tokens": 2997
}
] | [
"<think>\nOkay, let's tackle this query. The user wants to connect Morton Gould, the American composer and conductor, to the \"Benny Carter discography\" through multiple distinct paths. Each path must start with Morton Gould and end with a triple where the relationship is 'discography' and the tail is 'Benny Carte... | [
[
"Morton Gould",
"award received",
"Grammy Lifetime Achievement Award"
],
[
"Benny Carter",
"award received",
"Grammy Lifetime Achievement Award"
],
[
"Benny Carter",
"discography",
"Benny Carter discography"
]
] | [[[["morton gould", "member of", "american society of composers, authors, and publishers (ascap)"], ["american society of composers, authors, and publishers (ascap)", "members include", "benny carter"], ["benny carter", "discography", "benny carter discography"]], [["morton gould", "conducted", "american symphony orche... | [
"<think>\nOkay, let's tackle this query. The user wants to connect Morton Gould, the American composer and conductor, to the \"Benny Carter discography\" through multiple distinct paths. Each path must start with Morton Gould and end with a triple where the relationship is 'discography' and the tail is 'Benny Carte... | [[["morton gould", "member of", "american society of composers, authors, and publishers (ascap)"], ["american society of composers, authors, and publishers (ascap)", "members include", "benny carter"], ["benny carter", "discography", "benny carter discography"]], [["morton gould", "conducted", "american symphony orches... | "<think>\nOkay, let's tackle this query. The user wants to connect Morton Gould, the American composer and conductor, to the \"Benny Carter discography\" through multiple distinct paths. Each path must start with Morton Gould and end with a triple where the relationship is 'discography' and the tail is 'Benny Carter di... | 0 | 0 | 0 | 0 | 14 | 9 | 20 | [
[
1,
1,
1
],
[
1,
2,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
2,
1,
1
],
[
3,
1,
1
],
[
2,
2,
1
],
[
1,
3,
1
],
[
2,
3,
1
],
[
1,
2,
1
]
] | [
"{\n \"explanation\": \"Morton Gould is publicly known as a composer, conductor, and pianist; membership in ASCAP is a standard professional affiliation for a composer, making it a typical fact (T1). ASCAP's core purpose is to represent composers and publishers, so stating that Benny Carter is among its members di... | [
1,
2,
1,
1,
2,
3,
2,
3,
3,
2
] | [
1,
1,
1,
0,
0,
0,
1,
0,
0,
0
] | [
"{\n \"explanation\": \"All three triples involve real, identifiable entities. Morton Gould was a well‑known American composer and a member of ASCAP, so the first triple is accurate. ASCAP is a legitimate organization and Benny Carter, a celebrated jazz composer and saxophonist, was indeed among its members, makin... | [
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
0,
1
],
[
0,
1,
0
],
[
0,
1,
1
],
[
1,
1,
1
],
[
1,
0,
1
],
[
1,
0,
1
],
[
1,
0,
1
]
] | [
[
1,
1,
5
],
[
4,
3,
5
],
[
1,
1,
5
],
[
3,
3,
5
],
[
4,
4,
5
],
[
3,
3,
5
],
[
1,
1,
5
],
[
3,
3,
5
],
[
1,
5,
5
],
[
4,
3,
5
]
] | [
1,
3,
1,
3,
4,
3,
1,
3,
1,
3
] | [
"[\n {\n \"explanation\": \"Class A (subjects that are members of ASCAP): ASCAP is a major performance‑rights organization with hundreds of thousands of composers, authors and publishers as members, roughly 600 000. Class B (objects that Morton Gould is a member of): an individual composer typically belongs to ... | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 3 | 10 | ['<think>\nOkay, let\'s tackle this query. The user wants to connect Morton Gould, the American composer and conductor, to the "Benny Carter discography" through multiple distinct paths. Each path must start with Morton Gould and end with a triple where the relationship is \'discography\' and the tail is \'Benny Carter... | 7,726 | [
"['<think>\\nOkay, let\\'s tackle this query. The user wants to connect Morton Gould, the American composer and conductor, to the \"Benny Carter discography\" through multiple distinct paths. Each path must start with Morton Gould and end with a triple where the relationship is \\'discography\\' and the tail is \\'... | [
0
] | [
"Morton Gould",
"Benny Carter",
"Benny Carter discography",
"Columbia Records",
"Verve",
"Capitol",
"ASCAP",
"American Society of Composers, Authors, and Publishers",
"American Symphony Orchestra",
"Newport Jazz Festival",
"New York City",
"American Classical Music Hall of Fame",
"jazz hall ... | [
"collaborated with",
"worked with",
"member of",
"performed at",
"composed",
"conducted",
"released works of",
"performed by",
"members include",
"participants include",
"discography",
"taught",
"inducted into",
"contributed to",
"born in",
"mentor to"
] | 20 | 16 |
[
"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 | "Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ra(...TRUNCATED) | ["<think>\nOkay, let me try to figure out how to connect Max von Laue, the physicist known for X-ray(...TRUNCATED) | ["Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-r(...TRUNCATED) | [
{
"completion_tokens": 4898,
"prompt_tokens": 753,
"total_tokens": 5651
}
] | ["<think>\nOkay, let me try to figure out how to connect Max von Laue, the physicist known for X-ray(...TRUNCATED) | [["Max von Laue","award received","Nobel Prize in Physics"],["William Lawrence Bragg","award receive(...TRUNCATED) | "[[[[\"max von laue\", \"influenced\", \"dorothy crowfoot hodgkin\"], [\"dorothy crowfoot hodgkin\",(...TRUNCATED) | ["<think>\nOkay, let me try to figure out how to connect Max von Laue, the physicist known for X-ray(...TRUNCATED) | "[[[\"max von laue\", \"influenced\", \"dorothy crowfoot hodgkin\"], [\"dorothy crowfoot hodgkin\", (...TRUNCATED) | "\"<think>\\nOkay, let me try to figure out how to connect Max von Laue, the physicist known for X-r(...TRUNCATED) | 0 | 0 | 0 | 0 | 13 | 19 | 20 | [
[
2,
1
],
[
3,
1
],
[
1,
1,
1
],
[
2,
2,
1
],
[
1,
1,
2
],
[
2,
1
],
[
1,
2,
1
],
[
1,
2,
1
],
[
1,
1,
1
],
[
2,
1,
1
],
[
1,
1
],
[
1,
1,
1
]... | ["{\n \"explanation\": \"The first triple concerns Max von Laue, whose public identity is that of(...TRUNCATED) | [
2,
3,
1,
2,
1,
2,
2,
2,
1,
2,
1,
1
] | [
1,
1,
1,
1,
1,
1,
0,
0,
1,
0,
1,
1
] | ["{\n \"explanation\": \"Both triples involve real, identifiable individuals. Max von Laue was a (...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],[1.0,0.0,1.0],[1.0,0.0,1.0](...TRUNCATED) | [
[
4,
1
],
[
4,
1
],
[
1,
1,
1
],
[
5,
4,
1
],
[
4,
1,
1
],
[
4,
1
],
[
4,
4,
1
],
[
4,
4,
1
],
[
1,
1,
1
],
[
4,
4,
1
],
[
4,
1
],
[
2,
2,
1
]... | [
4,
4,
1,
4,
1,
4,
4,
4,
1,
4,
4,
2
] | ["[\n {\n \"explanation\": \"Class A (subjects that influenced Dorothy Crowfoot Hodgkin): she wa(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 2.666667 | 12 | "['<think>\\nOkay, let me try to figure out how to connect Max von Laue, the physicist known for X-r(...TRUNCATED) | 18,579 | ["['<think>\\nOkay, let me try to figure out how to connect Max von Laue, the physicist known for X-(...TRUNCATED) | [
0
] | ["Max von Laue","Dorothy Crowfoot Hodgkin","Rosalind Franklin","University of Berlin","Fritz Haber",(...TRUNCATED) | ["influenced","affiliated with","had as staff","advisor","influenced research in","used by","student(...TRUNCATED) | 19 | 12 |
[
"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 | "Query: What are different ways of connecting David Koechner, the American actor and comedian, and s(...TRUNCATED) | ["<think>\nOkay, let's see. I need to connect David Koechner to someone born in Newport Beach. The t(...TRUNCATED) | ["Query: What are different ways of connecting David Koechner, the American actor and comedian, and (...TRUNCATED) | [
{
"completion_tokens": 4210,
"prompt_tokens": 747,
"total_tokens": 4957
}
] | ["<think>\nOkay, let's see. I need to connect David Koechner to someone born in Newport Beach. The t(...TRUNCATED) | [["Twin Peaks","cast member","David Koechner"],["Twin Peaks","cast member","Rodney Rowland"],["Rodne(...TRUNCATED) | "[[[[\"david koechner\", \"co-starred with\", \"rob riggle\"], [\"rob riggle\", \"place of birth\", (...TRUNCATED) | ["<think>\nOkay, let's see. I need to connect David Koechner to someone born in Newport Beach. The t(...TRUNCATED) | "[[[\"david koechner\", \"co-starred with\", \"rob riggle\"], [\"rob riggle\", \"place of birth\", \(...TRUNCATED) | "\"<think>\\nOkay, let's see. I need to connect David Koechner to someone born in Newport Beach. The(...TRUNCATED) | 0 | 0 | 0 | 0 | 9 | 5 | 9 | [
[
1,
2
],
[
2,
1,
2
],
[
1,
1,
2
],
[
1,
1,
2
],
[
1,
1,
2
]
] | ["{\n \"explanation\": \"David Koechner is publicly known as a comedian and actor, so his core doma(...TRUNCATED) | [
1,
2,
1,
1,
1
] | [
0,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple involves real individuals, actor David Koechner and comed(...TRUNCATED) | [
[
1,
0
],
[
1,
0,
0
],
[
1,
1,
0
],
[
1,
0,
0
],
[
0,
0,
0
]
] | [
[
4,
3
],
[
1,
1,
1
],
[
1,
3,
3
],
[
3,
3,
4
],
[
4,
4,
3
]
] | [
4,
1,
1,
3,
4
] | ["[\n {\n \"explanation\": \"Class A (subjects that co-starred with Rob Riggle): Rob Riggle has (...TRUNCATED) | [
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
""
] | 2.8 | 5 | "['<think>\\nOkay, let\\'s see. I need to connect David Koechner to someone born in Newport Beach. T(...TRUNCATED) | 16,773 | ["['<think>\\nOkay, let\\'s see. I need to connect David Koechner to someone born in Newport Beach. (...TRUNCATED) | [
0
] | [
"David Koechner",
"Rob Riggle",
"Newport Beach",
"The Daily Show",
"University of Colorado Boulder"
] | [
"co-starred with",
"place of birth",
"attended (alma mater)",
"student"
] | 5 | 4 |
[
"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 | "Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and a(...TRUNCATED) | ["<think>\nOkay, let me try to figure this out. The user is asking for different ways to connect CD2(...TRUNCATED) | ["Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and (...TRUNCATED) | [
{
"completion_tokens": 2689,
"prompt_tokens": 744,
"total_tokens": 3433
}
] | ["<think>\nOkay, let me try to figure this out. The user is asking for different ways to connect CD2(...TRUNCATED) | [["CD2AP","genetic association","Alzheimer's disease"],["ATXN7L1","genetic association","Alzheimer's(...TRUNCATED) | "[[[[\"cd2ap\", \"encoded by\", \"cd2ap gene\"], [\"cd2ap gene\", \"located on\", \"dna molecule\"],(...TRUNCATED) | ["<think>\nOkay, let me try to figure this out. The user is asking for different ways to connect CD2(...TRUNCATED) | "[[[\"cd2ap\", \"encoded by\", \"cd2ap gene\"], [\"cd2ap gene\", \"located on\", \"dna molecule\"], (...TRUNCATED) | "\"<think>\\nOkay, let me try to figure this out. The user is asking for different ways to connect C(...TRUNCATED) | 0 | 0 | 0 | 0 | 14 | 16 | 19 | [
[
1,
1,
1
],
[
1,
1,
1,
1
],
[
1,
1,
1,
1
],
[
1,
1,
1,
1,
1,
1
],
[
1,
1,
1,
1
],
[
1,
1,
1,
1
]
] | ["{\n \"explanation\": \"The subject cd2ap is a protein, so its core domain tags are protein/cell(...TRUNCATED) | [
1,
1,
1,
1,
1,
1
] | [
1,
1,
0,
1,
0,
1
] | ["{\n \"explanation\": \"All three triples refer to real, identifiable entities and describe plausi(...TRUNCATED) | [[1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,0.0,1.0,1.0],[1.0,1.0,1.0,1.0,1.0,1.0],[0.0,1.0,1.0,1.0],[1.0,(...TRUNCATED) | [
[
5,
2,
4
],
[
4,
3,
3,
1
],
[
4,
5,
1,
1
],
[
3,
2,
2,
4,
4,
3
],
[
3,
3,
2,
1
],
[
1,
4,
1,
1
]
] | [
2,
3,
1,
2,
2,
1
] | ["[\n {\n \"explanation\": \"For the predicate 'encoded by' with object 'cd2ap gene', Class A co(...TRUNCATED) | [
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
""
] | 4.166667 | 6 | "['<think>\\nOkay, let me try to figure this out. The user is asking for different ways to connect C(...TRUNCATED) | 10,686 | ["['<think>\\nOkay, let me try to figure this out. The user is asking for different ways to connect (...TRUNCATED) | [
0
] | ["CD2AP","CD2AP gene","DNA molecule","reverse strand","T-cell signaling pathway","gene expression","(...TRUNCATED) | ["encoded by","located on","has strand orientation","part of","regulates","activates","involves","us(...TRUNCATED) | 18 | 15 |
[
"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 | "Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines?\n\nTa(...TRUNCATED) | ["<think>\nOkay, let's tackle this problem. The user wants to connect Kun Nong to someone born in De(...TRUNCATED) | ["Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines?\n\nT(...TRUNCATED) | [
{
"completion_tokens": 572,
"prompt_tokens": 738,
"total_tokens": 1310
}
] | ["<think>\nOkay, let's tackle this problem. The user wants to connect Kun Nong to someone born in De(...TRUNCATED) | [["Kun Nong","member of","Slipknot"],["Chris Fehn","member of","Slipknot"],["Chris Fehn","place of b(...TRUNCATED) | [[]] | ["<think>\nOkay, let's tackle this problem. The user wants to connect Kun Nong to someone born in De(...TRUNCATED) | [] | "\"<think>\\nOkay, let's tackle this problem. The user wants to connect Kun Nong to someone born in (...TRUNCATED) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | [
[]
] | [
"Hello! How can I assist you today?"
] | [
1
] | [
1
] | [
"Hello! How can I assist you today?"
] | [
[]
] | [
[]
] | [
0
] | [
"Hello! How can I assist you today?"
] | [
0
] | [
""
] | 0 | 0 | "['<think>\\nOkay, let\\'s tackle this problem. The user wants to connect Kun Nong to someone born i(...TRUNCATED) | 2,458 | ["['<think>\\nOkay, let\\'s tackle this problem. The user wants to connect Kun Nong to someone born (...TRUNCATED) | [
0
] | [] | [] | 0 | 0 |
[
"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 | "Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a sub(...TRUNCATED) | ["<think>\nOkay, let's tackle this problem. The user wants me to find different ways to connect enfu(...TRUNCATED) | ["Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a su(...TRUNCATED) | [
{
"completion_tokens": 7522,
"prompt_tokens": 759,
"total_tokens": 8281
}
] | ["<think>\nOkay, let's tackle this problem. The user wants me to find different ways to connect enfu(...TRUNCATED) | [["enfuvirtide","medical condition treated","HIV/AIDS"],["saquinavir","medical condition treated","H(...TRUNCATED) | "[[[[\"enfuvirtide\", \"combination therapy includes\", \"ritonavir\"], [\"ritonavir\", \"significan(...TRUNCATED) | ["<think>\nOkay, let's tackle this problem. The user wants me to find different ways to connect enfu(...TRUNCATED) | "[[[\"enfuvirtide\", \"combination therapy includes\", \"ritonavir\"], [\"ritonavir\", \"significant(...TRUNCATED) | "\"<think>\\nOkay, let's tackle this problem. The user wants me to find different ways to connect en(...TRUNCATED) | 0 | 0 | 0 | 0 | 3 | 10 | 15 | [
[
1,
2
],
[
1,
2
],
[
1,
1
],
[
1,
1,
1
],
[
2,
2,
2
],
[
2,
2,
2
],
[
3,
2
],
[
3,
1
],
[
1,
1,
1
],
[
3,
1,
1
]
] | ["{\n \"explanation\": \"Enfuvirtide is publicly known as an HIV fusion‑inhibitor antiretroviral (...TRUNCATED) | [
1,
1,
1,
1,
2,
2,
3,
3,
1,
3
] | [
0,
1,
0,
0,
0,
0,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple links enfuvirtide, an HIV fusion inhibitor, with ritonavi(...TRUNCATED) | [[1.0,0.0],[1.0,1.0],[1.0,0.0],[0.0,1.0,0.0],[0.0,1.0,0.0],[0.0,1.0,1.0],[0.0,1.0],[0.0,1.0],[0.0,1.(...TRUNCATED) | [
[
4,
3
],
[
4,
4
],
[
4,
4
],
[
2,
3,
3
],
[
3,
3,
4
],
[
3,
3,
4
],
[
4,
4
],
[
4,
3
],
[
3,
4,
4
],
[
4,
3,
4
]
] | [
4,
4,
4,
2,
3,
3,
4,
4,
3,
3
] | ["[\n {\n \"explanation\": \"Class A (subjects that include ritonavir in a combination therapy):(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 2.5 | 10 | "['<think>\\nOkay, let\\'s tackle this problem. The user wants me to find different ways to connect (...TRUNCATED) | 26,938 | ["['<think>\\nOkay, let\\'s tackle this problem. The user wants me to find different ways to connect(...TRUNCATED) | [
0
] | ["Enfuvirtide","Venlafaxine","Ritonavir","Efavirenz","Nelfinavir","Verapamil","Cyclosporine","Quinid(...TRUNCATED) | ["combination therapy includes","significant drug interaction","interacts with","inhibits","substrat(...TRUNCATED) | 19 | 7 |
[
"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 | "Query: What are different ways of connecting Bela B, the German musician, and someone who is the un(...TRUNCATED) | ["<think>\nOkay, let's tackle this problem step by step. The user wants to connect Bela B, the Germa(...TRUNCATED) | ["Query: What are different ways of connecting Bela B, the German musician, and someone who is the u(...TRUNCATED) | [
{
"completion_tokens": 1721,
"prompt_tokens": 748,
"total_tokens": 2469
}
] | ["<think>\nOkay, let's tackle this problem step by step. The user wants to connect Bela B, the Germa(...TRUNCATED) | [["Bela B","member of","Die Ärzte"],["Hagen Liebing","member of","Die Ärzte"],["Hagen Liebing","un(...TRUNCATED) | "[[[[\"bela b\", \"member of\", \"b\\u00f6hse onkelz\"], [\"b\\u00f6hse onkelz\", \"collaborated wit(...TRUNCATED) | ["<think>\nOkay, let's tackle this problem step by step. The user wants to connect Bela B, the Germa(...TRUNCATED) | "[[[\"bela b\", \"member of\", \"b\\u00f6hse onkelz\"], [\"b\\u00f6hse onkelz\", \"collaborated with(...TRUNCATED) | "\"<think>\\nOkay, let's tackle this problem step by step. The user wants to connect Bela B, the Ger(...TRUNCATED) | 0 | 0 | 0 | 0 | 8 | 7 | 12 | [
[
2,
2,
3,
3
],
[
1,
1,
3
],
[
1,
3,
3,
2
],
[
1,
3,
3
],
[
3,
3,
3
]
] | ["{\n \"explanation\": \"Bela B is publicly known as a German musician and drummer for Die Ärzte, (...TRUNCATED) | [
3,
1,
3,
3,
3
] | [
0,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple links Bela B, a real German musician known for Die Ärzte(...TRUNCATED) | [
[
0,
1,
0,
0
],
[
0,
0,
0
],
[
0,
0,
0,
0
],
[
1,
0,
0
],
[
1,
0,
0
]
] | [
[
5,
4,
5,
5
],
[
3,
1,
5
],
[
5,
5,
5,
5
],
[
3,
4,
5
],
[
3,
4,
5
]
] | [
4,
1,
5,
3,
3
] | ["[\n {\n \"explanation\": \"Class A (subjects that are members of Böhse Onkelz) includes the t(...TRUNCATED) | [
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
""
] | 3.4 | 5 | "['<think>\\nOkay, let\\'s tackle this problem step by step. The user wants to connect Bela B, the G(...TRUNCATED) | 5,742 | ["['<think>\\nOkay, let\\'s tackle this problem step by step. The user wants to connect Bela B, the (...TRUNCATED) | [
0
] | ["Bela B","Anja Caspary","Hagen Liebing","Böhse Onkelz","Feine Sahne Fischfilet","German punk scene(...TRUNCATED) | ["unmarried partner","collaborated with","performed at","co-performer at","signed to","member of","i(...TRUNCATED) | 17 | 12 |
[
"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 | "Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jakub(...TRUNCATED) | ["<think>\nOkay, let's tackle this problem. The user wants to connect Nicolas Chopin to someone who (...TRUNCATED) | ["Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jaku(...TRUNCATED) | [
{
"completion_tokens": 1488,
"prompt_tokens": 748,
"total_tokens": 2236
}
] | ["<think>\nOkay, let's tackle this problem. The user wants to connect Nicolas Chopin to someone who (...TRUNCATED) | [["Nicolas Chopin","child","Frédéric Chopin"],["Tekla Justyna Chopin","child","Frédéric Chopin"](...TRUNCATED) | [[]] | ["<think>\nOkay, let's tackle this problem. The user wants to connect Nicolas Chopin to someone who (...TRUNCATED) | [] | "\"<think>\\nOkay, let's tackle this problem. The user wants to connect Nicolas Chopin to someone wh(...TRUNCATED) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | [
[]
] | [
"Hello! How can I assist you today?"
] | [
1
] | [
1
] | [
"Hello! How can I assist you today?"
] | [
[]
] | [
[]
] | [
0
] | [
"Hello! How can I assist you today?"
] | [
0
] | [
""
] | 0 | 0 | "[\"<think>\\nOkay, let's tackle this problem. The user wants to connect Nicolas Chopin to someone w(...TRUNCATED) | 6,445 | ["[\"<think>\\nOkay, let's tackle this problem. The user wants to connect Nicolas Chopin to someone (...TRUNCATED) | [
0
] | ["Nicolas Chopin","Frédéric Chopin","Jakub Krzyżanowski","Jakub Krzyżanowski's father","Chopin f(...TRUNCATED) | [
"father of",
"namesake",
"faculty member at",
"born in",
"member of",
"teacher of",
"composed works"
] | 9 | 7 |
[
"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 | "Query: What are different ways of connecting George H. W. Bush, the 41st President of the United St(...TRUNCATED) | ["<think>\nOkay, let me try to figure out how to connect George H. W. Bush to someone who was the Fi(...TRUNCATED) | ["Query: What are different ways of connecting George H. W. Bush, the 41st President of the United S(...TRUNCATED) | [
{
"completion_tokens": 3932,
"prompt_tokens": 765,
"total_tokens": 4697
}
] | ["<think>\nOkay, let me try to figure out how to connect George H. W. Bush to someone who was the Fi(...TRUNCATED) | [["George H. W. Bush","child","George W. Bush"],["Barbara Bush","child","George W. Bush"],["Barbara (...TRUNCATED) | "[[[[\"george h. w. bush\", \"spouse\", \"barbara bush\"], [\"barbara bush\", \"position held\", \"f(...TRUNCATED) | ["<think>\nOkay, let me try to figure out how to connect George H. W. Bush to someone who was the Fi(...TRUNCATED) | "[[[\"george h. w. bush\", \"spouse\", \"barbara bush\"], [\"barbara bush\", \"position held\", \"fi(...TRUNCATED) | "\"<think>\\nOkay, let me try to figure out how to connect George H. W. Bush to someone who was the (...TRUNCATED) | 0 | 0 | 0 | 0 | 5 | 4 | 7 | [
[
2,
1
],
[
2,
2,
1
],
[
2,
1
],
[
1,
1,
2,
1
]
] | ["{\n \"explanation\": \"George H. W. Bush is publicly known primarily as a former U.S. President a(...TRUNCATED) | [
2,
2,
2,
2
] | [
1,
1,
1,
1
] | ["{\n \"explanation\": \"Both triples refer to real, well‑known individuals and accurately descri(...TRUNCATED) | [
[
1,
1
],
[
1,
1,
1
],
[
1,
1
],
[
1,
1,
1,
1
]
] | [
[
5,
4
],
[
5,
5,
4
],
[
5,
4
],
[
1,
1,
5,
4
]
] | [
5,
5,
5,
1
] | ["[\n {\n \"explanation\": \"Class A (subjects that could be the spouse of Barbara Bush): Barbar(...TRUNCATED) | [
1,
1,
1,
1
] | [
"",
"",
"",
""
] | 2.75 | 4 | "['<think>\\nOkay, let me try to figure out how to connect George H. W. Bush to someone who was the (...TRUNCATED) | 16,658 | ["['<think>\\nOkay, let me try to figure out how to connect George H. W. Bush to someone who was the(...TRUNCATED) | [
0
] | ["George H. W. Bush","Barbara Bush","First Lady of the United States","Dorothy Bush","Dan Quayle","M(...TRUNCATED) | ["spouse","position held","child","father-in-law","parent","president during","protected by","member(...TRUNCATED) | 29 | 13 |
[
"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 | "Query: What are different ways of connecting INTS7, a protein involved in various cellular processe(...TRUNCATED) | ["<think>\nOkay, let's tackle this problem step by step. The user wants to connect INTS7, a protein,(...TRUNCATED) | ["Query: What are different ways of connecting INTS7, a protein involved in various cellular process(...TRUNCATED) | [
{
"completion_tokens": 3727,
"prompt_tokens": 750,
"total_tokens": 4477
}
] | ["<think>\nOkay, let's tackle this problem step by step. The user wants to connect INTS7, a protein,(...TRUNCATED) | [["INTS7","genetic association","bipolar disorder"],["MCTP1","genetic association","bipolar disorder(...TRUNCATED) | "[[[[\"ints7\", \"part of\", \"integrator complex\"], [\"integrator complex\", \"processes\", \"snrn(...TRUNCATED) | ["<think>\nOkay, let's tackle this problem step by step. The user wants to connect INTS7, a protein,(...TRUNCATED) | "[[[\"ints7\", \"part of\", \"integrator complex\"], [\"integrator complex\", \"processes\", \"snrna(...TRUNCATED) | "\"<think>\\nOkay, let's tackle this problem step by step. The user wants to connect INTS7, a protei(...TRUNCATED) | 0 | 0 | 0 | 0 | 10 | 12 | 13 | [
[
1,
1,
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1,
1,
2
],
[
1,
1,
1,
1
]
] | ["{\n \"explanation\": \"Each triple describes a fact that is directly tied to the primary scientif(...TRUNCATED) | [
1,
1,
1,
1
] | [
0,
0,
1,
0
] | ["{\n \"explanation\": \"The first triple correctly identifies INTS7 as a subunit of the Integrator(...TRUNCATED) | [
[
1,
1,
1,
1,
0
],
[
0,
1,
1
],
[
1,
1,
1,
1,
1
],
[
0,
1,
1,
0
]
] | [
[
4,
5,
3,
1,
1
],
[
4,
3,
1
],
[
1,
3,
3,
1,
1
],
[
4,
2,
5,
2
]
] | [
1,
3,
1,
2
] | ["[\n {\n \"explanation\": \"Class A (subjects that are part of the integrator complex) includes(...TRUNCATED) | [
1,
1,
1,
1
] | [
"",
"",
"",
""
] | 4.25 | 4 | "['<think>\\nOkay, let\\'s tackle this problem step by step. The user wants to connect INTS7, a prot(...TRUNCATED) | 15,097 | ["['<think>\\nOkay, let\\'s tackle this problem step by step. The user wants to connect INTS7, a pro(...TRUNCATED) | [
0
] | ["INTS7","Integrator complex","snRNA","spliceosome","ABCB4 mRNA","gallbladder","RNA processing","gen(...TRUNCATED) | ["part of","involved in","processes","splices","expressed in","regulates","interacts with","required(...TRUNCATED) | 14 | 10 |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 3