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 | all_response_tokens listlengths 1 1 | all_reasoning_tokens listlengths 1 1 | raw_path_prediction listlengths 1 1 | source_path listlengths 3 3 | parsed_paths stringlengths 4 4.52k | reasoning_paths listlengths 1 1 | paths_0 stringlengths 2 4.52k | reasoning_0 stringlengths 1.99k 5.59k | 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 36 | entity_lexical_uniqueness_0 int64 0 56 | num_triples_0 int64 0 59 | uniqueness_scores_0 listlengths 1 30 | unique_raw_response_0 listlengths 1 30 | max_uniqueness_score_0 listlengths 1 30 | factuality_scores_0 listlengths 1 30 | raw_responses_factuality_0 listlengths 1 30 | parsed_scores_factuality_0 listlengths 1 30 | raw_salience_scores_0 listlengths 1 30 | min_salience_scores_0 listlengths 1 30 | salience_raw_responses_0 listlengths 1 30 | validity_per_path_0 listlengths 1 30 | validity_reasons_0 listlengths 1 30 | avg_path_length_0 float64 0 10.8 | num_paths_0 float64 0 30 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[
"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>\nLet me analyze this query carefully. I need to find connection paths from \"Morton Gould\" (American composer and conductor) to \"Benny Carter discography\" (the discography of Benny Carter, who has a notable discography in music).\n\nThe paths must:\n1. Start with Morton Gould\n2. End with a triple where... | [
"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, ... | [
2037
] | [
null
] | [
"<think>\nLet me analyze this query carefully. I need to find connection paths from \"Morton Gould\" (American composer and conductor) to \"Benny Carter discography\" (the discography of Benny Carter, who has a notable discography in music).\n\nThe paths must:\n1. Start with Morton Gould\n2. End with a triple where... | [
[
"Morton Gould",
"award received",
"Grammy Lifetime Achievement Award"
],
[
"Benny Carter",
"award received",
"Grammy Lifetime Achievement Award"
],
[
"Benny Carter",
"discography",
"Benny Carter discography"
]
] | [[[["morton gould", "recorded for", "rca records"], ["rca records", "recorded", "benny carter"], ["benny carter", "discography", "benny carter discography"]], [["morton gould", "worked in", "american music industry"], ["american music industry", "includes musician", "benny carter"], ["benny carter", "discography", "ben... | [
"<think>\nLet me analyze this query carefully. I need to find connection paths from \"Morton Gould\" (American composer and conductor) to \"Benny Carter discography\" (the discography of Benny Carter, who has a notable discography in music).\n\nThe paths must:\n1. Start with Morton Gould\n2. End with a triple where... | [[["morton gould", "recorded for", "rca records"], ["rca records", "recorded", "benny carter"], ["benny carter", "discography", "benny carter discography"]], [["morton gould", "worked in", "american music industry"], ["american music industry", "includes musician", "benny carter"], ["benny carter", "discography", "benn... | "<think>\nLet me analyze this query carefully. I need to find connection paths from \"Morton Gould\" (American composer and conductor) to \"Benny Carter discography\" (the discography of Benny Carter, who has a notable discography in music).\n\nThe paths must:\n1. Start with Morton Gould\n2. End with a triple where rel... | 0 | 0 | 0 | 0 | 13 | 9 | 16 | [
[
1,
1,
1
],
[
1,
1,
1
],
[
2,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
2,
1
]
] | [
"{\n \"explanation\": \"For each triple, I identified the subject's primary public identity and then assessed how directly the predicate‑object relates to that core domain. Morton Gould is best known as a composer and conductor; recording for a major label like RCA Records is a standard professional activity for s... | [
1,
1,
2,
1,
1,
1,
1,
2
] | [
0,
1,
1,
1,
1,
1,
1,
0
] | [
"{\n \"explanation\": \"The first triple links the American composer and conductor Morton Gould to RCA Records with the relation 'recorded for'. Morton Gould did make recordings for RCA Victor, the classical arm of RCA Records, so both entities exist and the relationship is accurate. The second triple states that ... | [
[
1,
1,
0
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
0,
1
]
] | [
[
2,
2,
5
],
[
1,
1,
5
],
[
2,
3,
5
],
[
2,
1,
5
],
[
1,
3,
5
],
[
2,
2,
5
],
[
1,
1,
5
],
[
4,
3,
3
]
] | [
2,
1,
2,
1,
1,
2,
1,
3
] | [
"[\n {\n \"explanation\": \"Class A (subjects that recorded for RCA Records): RCA Records has been a major label for over a century and has signed thousands of artists; a rough estimate is about 3000 distinct artists. Class B (objects that Morton Gould recorded for): Morton Gould was primarily associated with a... | [
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
""
] | 3 | 8 |
[
"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.
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 Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist? | Max von Laue | chemist | occupation | 1 | Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual t... | [
"<think>\nLet me think about Max von Laue and how he might connect to chemists.\n\nMax von Laue was a German physicist (1879-1960) who won the Nobel Prize in Physics in 1912 for his work on X-ray diffraction. \n\nTo find connections between Max von Laue and chemists, I need to think about:\n1. People he directly kn... | [
"Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of fa... | [
2514
] | [
null
] | [
"<think>\nLet me think about Max von Laue and how he might connect to chemists.\n\nMax von Laue was a German physicist (1879-1960) who won the Nobel Prize in Physics in 1912 for his work on X-ray diffraction. \n\nTo find connections between Max von Laue and chemists, I need to think about:\n1. People he directly kn... | [
[
"Max von Laue",
"award received",
"Nobel Prize in Physics"
],
[
"William Lawrence Bragg",
"award received",
"Nobel Prize in Physics"
],
[
"William Lawrence Bragg",
"occupation",
"chemist"
]
] | [[[["max von laue", "worked at", "kaiser wilhelm institute"], ["kaiser wilhelm institute", "employed", "otto hahn"], ["otto hahn", "occupation", "chemist"]], [["max von laue", "pioneered", "x-ray diffraction"], ["x-ray diffraction", "technique used by", "dorothy hodgkin"], ["dorothy hodgkin", "occupation", "chemist"]],... | [
"<think>\nLet me think about Max von Laue and how he might connect to chemists.\n\nMax von Laue was a German physicist (1879-1960) who won the Nobel Prize in Physics in 1912 for his work on X-ray diffraction. \n\nTo find connections between Max von Laue and chemists, I need to think about:\n1. People he directly kn... | [[["max von laue", "worked at", "kaiser wilhelm institute"], ["kaiser wilhelm institute", "employed", "otto hahn"], ["otto hahn", "occupation", "chemist"]], [["max von laue", "pioneered", "x-ray diffraction"], ["x-ray diffraction", "technique used by", "dorothy hodgkin"], ["dorothy hodgkin", "occupation", "chemist"]], ... | "<think>\nLet me think about Max von Laue and how he might connect to chemists.\n\nMax von Laue was a German physicist (1879-1960) who won the Nobel Prize in Physics in 1912 for his work on X-ray diffraction. \n\nTo find connections between Max von Laue and chemists, I need to think about:\n1. People he directly knew o... | 0 | 0 | 0 | 0 | 20 | 24 | 31 | [
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1,
1,
2,
1
],
[
1,
1,
1,
1
],
[
1,
2,
1,
1
],
[
1,
1,
1,
1
],
[
1,
1,
1,
2,
1
],
[
1,
1,
1,
1... | [
"{\n \"explanation\": \"Max von Laue is publicly known as a Nobel‑winning physicist famous for X‑ray diffraction, so his employment at the Kaiser Wilhelm Institute is a standard biographical detail (T1). The Kaiser Wilhelm Institute is recognized as a major German research organization; noting that it employed the... | [
1,
1,
1,
2,
1,
2,
1,
2,
1,
3
] | [
1,
1,
1,
0,
1,
1,
0,
0,
0,
0
] | [
"{\n \"explanation\": \"All three triples involve real, identifiable historical figures and institutions. Max von Laue was a director at the Kaiser Wilhelm Institute for Physics, so the 'worked at' relation is correct. The Kaiser Wilhelm Institute (specifically the chemistry branch) employed Otto Hahn, making the ... | [
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
0,
1,
1,
1,
1
],
[
1,
1,
1,
1
],
[
1,
1,
1,
1
],
[
1,
1,
0,
1
],
[
1,
1,
0,
1,
1
],
[
0,
1,
1,
1... | [
[
2,
2,
1
],
[
5,
1,
1
],
[
1,
1,
1
],
[
2,
2,
2,
2,
2,
1
],
[
4,
2,
2,
1
],
[
3,
5,
3,
1
],
[
5,
4,
5,
1
],
[
1,
1,
4,
3,
1
],
[
5,
4,
4,
3... | [
2,
1,
1,
2,
2,
3,
4,
1,
3,
5
] | [
"[\n {\n \"explanation\": \"Class A (who worked at the Kaiser Wilhelm Institute): the institute was a major research organization that employed hundreds to thousands of scientists over many decades, so I estimate roughly 2,000 individuals. Class B (where Max von Laue worked): historically Max von Laue held a fe... | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 4.1 | 10 |
[
"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>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) | [
1844
] | [
0
] | ["<think>I need to find connection paths from David Koechner (American actor and comedian) to someon(...TRUNCATED) | [["Twin Peaks","cast member","David Koechner"],["Twin Peaks","cast member","Rodney Rowland"],["Rodne(...TRUNCATED) | "[[[[\"david koechner\", \"appeared in\", \"anchorman\"], [\"anchorman\", \"featured actor\", \"chri(...TRUNCATED) | ["<think>I need to find connection paths from David Koechner (American actor and comedian) to someon(...TRUNCATED) | "[[[\"david koechner\", \"appeared in\", \"anchorman\"], [\"anchorman\", \"featured actor\", \"chris(...TRUNCATED) | "\"<think>I need to find connection paths from David Koechner (American actor and comedian) to someo(...TRUNCATED) | 0 | 0 | 0 | 0 | 32 | 33 | 42 | [[1,1,1,1,1,1,1,1,1,1,1,1],[1,1,1,1,2,1,2,2,1,1,2,1,2,2],[1,1,1,1,1,2,2],[1,1,1,2,2,2,2,2],[1,1,2,2,(...TRUNCATED) | ["{\n \"explanation\": \"For each triple, I identified the subject's primary public identity (e.g.,(...TRUNCATED) | [
1,
2,
2,
2,
2
] | [
0,
0,
0,
0,
0
] | ["{\n \"explanation\": \"I examined each triple for real entities and whether the stated relationsh(...TRUNCATED) | [[1.0,0.0,0.0,1.0,0.0,1.0,0.0,1.0,1.0,1.0,0.0,0.0],[1.0,1.0,1.0,1.0,0.0,1.0,0.0,1.0,1.0,1.0,0.0,1.0,(...TRUNCATED) | [[4,4,3,4,5,3,3,3,1,4,4,4],[3,4,4,5,5,2,4,5,3,3,1,3,4,5],[3,2,2,1,3,4,4],[3,3,2,1,2,4,2,2],[3,3,4,4,(...TRUNCATED) | [
1,
1,
1,
1,
3
] | ["[\n {\n \"explanation\": \"Class A (subjects that appeared in Anchorman): the film has roughly(...TRUNCATED) | [
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
""
] | 9.4 | 5 |
[
"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>\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) | [
2142
] | [
null
] | ["<think>\nLet me analyze this query carefully:\n\n1. Start entity: CD2AP (a protein involved in cel(...TRUNCATED) | [["CD2AP","genetic association","Alzheimer's disease"],["ATXN7L1","genetic association","Alzheimer's(...TRUNCATED) | "[[[[\"cd2ap\", \"encoded by\", \"cd2ap gene\"], [\"cd2ap gene\", \"strand orientation\", \"reverse (...TRUNCATED) | ["<think>\nLet me analyze this query carefully:\n\n1. Start entity: CD2AP (a protein involved in cel(...TRUNCATED) | "[[[\"cd2ap\", \"encoded by\", \"cd2ap gene\"], [\"cd2ap gene\", \"strand orientation\", \"reverse s(...TRUNCATED) | "\"<think>\\nLet me analyze this query carefully:\\n\\n1. Start entity: CD2AP (a protein involved in(...TRUNCATED) | 0 | 0 | 0 | 0 | 14 | 26 | 27 | [
[
1,
3
],
[
1,
1,
1
],
[
1,
1,
1,
3
],
[
1,
1,
1,
3
],
[
1,
1,
1,
1,
1
],
[
1,
1,
3
],
[
1,
1,
1,
3
],
[
1,
1,
1,
3
],
[
1,
1,
3
],
[
1,
1,
... | ["{\n \"explanation\": \"The subject 'cd2ap' is a protein, so its core domain tags are protein/gene(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
1,
0,
1,
0,
0,
1,
0,
1,
0,
1
] | ["{\n \"explanation\": \"The first triple links the protein CD2AP (written as \\\"cd2ap\\\") to its(...TRUNCATED) | [[1.0,1.0],[1.0,1.0,0.0],[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],[1.0,1.0,1.0],[1.(...TRUNCATED) | [
[
5,
1
],
[
4,
5,
1
],
[
4,
3,
5,
1
],
[
3,
4,
5,
1
],
[
3,
4,
4,
5,
1
],
[
4,
4,
1
],
[
1,
2,
5,
1
],
[
1,
2,
5,
1
],
[
3,
5,
1
],
[
4,
4,
... | [
5,
4,
3,
3,
3,
4,
1,
1,
3,
4
] | ["[\n {\n \"explanation\": \"Class A (subject‑variation): all subjects that are encoded by the(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 3.7 | 10 |
[
"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>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) | [
946
] | [
0
] | ["<think>Let me think about who Kun Nong is and potential connections to someone born in Des Moines.(...TRUNCATED) | [["Kun Nong","member of","Slipknot"],["Chris Fehn","member of","Slipknot"],["Chris Fehn","place of b(...TRUNCATED) | "[[[[\"kun nong\", \"collaborated with\", \"unknown des moines native\"], [\"unknown des moines nati(...TRUNCATED) | ["<think>Let me think about who Kun Nong is and potential connections to someone born in Des Moines.(...TRUNCATED) | "[[[\"kun nong\", \"collaborated with\", \"unknown des moines native\"], [\"unknown des moines nativ(...TRUNCATED) | "\"<think>Let me think about who Kun Nong is and potential connections to someone born in Des Moines(...TRUNCATED) | 0 | 0 | 0 | 0 | 1 | 1 | 1 | [
[
3,
1
]
] | ["{\n \"explanation\": \"The subject 'kun nong' is best known as a legendary Chinese emperor or myt(...TRUNCATED) | [
3
] | [
0
] | ["{\n \"explanation\": \"The first triple links \\\"kun nong\\\" to \\\"unknown des moines native\\(...TRUNCATED) | [
[
0,
0
]
] | [
[
5,
1
]
] | [
5
] | ["[\n {\n \"explanation\": \"Class A (subjects that collaborated with the unknown Des Moines nat(...TRUNCATED) | [
1
] | [
""
] | 2 | 1 |
[
"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>\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) | [
2262
] | [
null
] | ["<think>\nLet me analyze this query systematically.\n\nThe query asks for connection paths from:\n-(...TRUNCATED) | [["enfuvirtide","medical condition treated","HIV/AIDS"],["saquinavir","medical condition treated","H(...TRUNCATED) | "[[[[\"enfuvirtide\", \"used to treat\", \"hiv infection\"], [\"hiv infection\", \"standard treatmen(...TRUNCATED) | ["<think>\nLet me analyze this query systematically.\n\nThe query asks for connection paths from:\n-(...TRUNCATED) | "[[[\"enfuvirtide\", \"used to treat\", \"hiv infection\"], [\"hiv infection\", \"standard treatment(...TRUNCATED) | "\"<think>\\nLet me analyze this query systematically.\\n\\nThe query asks for connection paths from(...TRUNCATED) | 0 | 0 | 0 | 0 | 21 | 19 | 26 | [
[
1,
1,
1,
1,
2
],
[
1,
1,
1,
1,
1
],
[
1,
2,
2,
1,
3
],
[
1,
2,
1,
2
],
[
1,
2,
1,
2
],
[
1,
1,
1,
1,
1,
1
],
[
1,
1,
1,
3
]
] | ["{\n \"explanation\": \"Enfuvirtide is primarily known as an antiretroviral drug used to treat HIV(...TRUNCATED) | [
1,
1,
2,
2,
2,
1,
1
] | [
0,
0,
0,
1,
0,
0,
0
] | ["{\n \"explanation\": \"The first four triples are accurate: enfuvirtide is an approved drug for t(...TRUNCATED) | [[1.0,1.0,1.0,1.0,0.0],[1.0,1.0,1.0,1.0,0.0],[1.0,1.0,1.0,1.0,0.0],[1.0,1.0,1.0,1.0],[1.0,0.0,1.0,1.(...TRUNCATED) | [
[
4,
5,
5,
5,
3
],
[
4,
4,
5,
5,
4
],
[
5,
4,
4,
4,
4
],
[
3,
3,
3,
4
],
[
4,
4,
3,
4
],
[
5,
5,
5,
5,
5,
4
],
[
4,
4,
4,
3
]
] | [
4,
4,
4,
3,
3,
5,
4
] | ["[\n {\n \"explanation\": \"Class A (subjects that are used to treat HIV infection) includes al(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
""
] | 4.714286 | 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>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) | [
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","Die Ärzte"],["Hagen Liebing","member of","Die Ärzte"],["Hagen Liebing","un(...TRUNCATED) | "[[[[\"bela b\", \"member of band\", \"die \\u00e4rzte\"], [\"die \\u00e4rzte\", \"collaborated with(...TRUNCATED) | ["<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) | "\"<think>Let me analyze this query step by step.\\n\\nI need to find connection paths from \\\"Bela(...TRUNCATED) | 0 | 0 | 0 | 0 | 13 | 9 | 14 | [
[
1,
2,
2,
3
],
[
1,
1,
3
],
[
1,
1,
3
],
[
1,
1,
2,
3
],
[
1,
1,
3
],
[
1,
1,
2
]
] | ["{\n \"explanation\": \"Bela B is best known as a German musician and the drummer of Die Ärzte, s(...TRUNCATED) | [
2,
1,
1,
2,
1,
1
] | [
0,
1,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple is correct: Bela B (real name Dirk Felsenheimer) is a fou(...TRUNCATED) | [
[
1,
1,
1,
0
],
[
1,
1,
1
],
[
1,
1,
0
],
[
0,
0,
1,
1
],
[
1,
1,
0
],
[
1,
0,
0
]
] | [
[
5,
4,
4,
5
],
[
2,
2,
5
],
[
1,
1,
5
],
[
5,
3,
3,
5
],
[
1,
1,
5
],
[
4,
4,
5
]
] | [
4,
2,
1,
3,
1,
4
] | ["[\n {\n \"explanation\": \"Class A (subjects that are members of the band Die Ärzte): the ban(...TRUNCATED) | [
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
""
] | 3.333333 | 6 |
[
"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>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) | [
989
] | [
0
] | ["<think>Let me think about this query. I need to find connection paths from \"Nicolas Chopin\" to s(...TRUNCATED) | [["Nicolas Chopin","child","Frédéric Chopin"],["Tekla Justyna Chopin","child","Frédéric Chopin"](...TRUNCATED) | "[[[[\"nicolas chopin\", \"father of\", \"fr\\u00e9d\\u00e9ric chopin\"], [\"fr\\u00e9d\\u00e9ric ch(...TRUNCATED) | ["<think>Let me think about this query. I need to find connection paths from \"Nicolas Chopin\" to s(...TRUNCATED) | "[[[\"nicolas chopin\", \"father of\", \"fr\\u00e9d\\u00e9ric chopin\"], [\"fr\\u00e9d\\u00e9ric cho(...TRUNCATED) | "\"<think>Let me think about this query. I need to find connection paths from \\\"Nicolas Chopin\\\"(...TRUNCATED) | 0 | 0 | 0 | 0 | 6 | 6 | 6 | [
[
1,
2,
3
],
[
2,
3,
1
],
[
2,
1,
3
]
] | ["{\n \"explanation\": \"The first triple links Nicolas Chopin to his most publicly known role – (...TRUNCATED) | [
2,
3,
2
] | [
0,
0,
0
] | ["{\n \"explanation\": \"The first triple correctly identifies Nicolas (Mikołaj) Chopin as the fat(...TRUNCATED) | [
[
1,
0,
0
],
[
1,
1,
0
],
[
1,
1,
0
]
] | [
[
5,
4,
4
],
[
1,
1,
5
],
[
1,
4,
1
]
] | [
4,
1,
1
] | ["[\n {\n \"explanation\": \"Class A (subjects that are \\\"father of\\\" Frédéric Chopin) inc(...TRUNCATED) | [
1,
0,
1
] | [
"",
"there is no continuity for the pair (1, 2)",
""
] | 3 | 3 |
[
"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>\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) | [
1619
] | [
null
] | ["<think>\nLet me think about how to connect George H. W. Bush (41st President) to someone who held (...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>\nLet me think about how to connect George H. W. Bush (41st President) to someone who held (...TRUNCATED) | "[[[\"george h. w. bush\", \"spouse\", \"barbara bush\"], [\"barbara bush\", \"position held\", \"fi(...TRUNCATED) | "\"<think>\\nLet me think about how to connect George H. W. Bush (41st President) to someone who hel(...TRUNCATED) | 0 | 0 | 0 | 0 | 3 | 5 | 5 | [
[
1,
1
],
[
2,
2,
1
],
[
1,
2,
1
]
] | ["{\n \"explanation\": \"For the first triple, George H. W. Bush is publicly known primarily as a U(...TRUNCATED) | [
1,
2,
2
] | [
1,
1,
1
] | ["{\n \"explanation\": \"Both triples refer to real, well‑known individuals and correctly describ(...TRUNCATED) | [
[
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
]
] | [
[
5,
4
],
[
5,
5,
4
],
[
5,
5,
4
]
] | [
5,
5,
5
] | ["[\n {\n \"explanation\": \"Class A (subjects that have the predicate spouse with object Barbar(...TRUNCATED) | [
1,
1,
1
] | [
"",
"",
""
] | 2.666667 | 3 |
[
"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>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) | [
1827
] | [
0
] | ["<think>Let me break down this task:\n\n1. Start entity: INTS7 (a protein)\n2. End condition: A tri(...TRUNCATED) | [["INTS7","genetic association","bipolar disorder"],["MCTP1","genetic association","bipolar disorder(...TRUNCATED) | "[[[[\"ints7\", \"component of\", \"integrator complex\"], [\"integrator complex\", \"regulates tran(...TRUNCATED) | ["<think>Let me break down this task:\n\n1. Start entity: INTS7 (a protein)\n2. End condition: A tri(...TRUNCATED) | "[[[\"ints7\", \"component of\", \"integrator complex\"], [\"integrator complex\", \"regulates trans(...TRUNCATED) | "\"<think>Let me break down this task:\\n\\n1. Start entity: INTS7 (a protein)\\n2. End condition: A(...TRUNCATED) | 0 | 0 | 0 | 0 | 18 | 25 | 26 | [[1,1,3],[1,2,2],[1,1,2],[1,2,1,1],[1,1,2],[1,1,1],[1,1,2],[2,1,1],[1,3,2],[1,3,3],[2,1,2],[1,1,1,1](...TRUNCATED) | ["{\n \"explanation\": \"The first triple links INT S7 to the Integrator complex, which is exactly (...TRUNCATED) | [
1,
2,
1,
2,
1,
1,
1,
2,
3,
3,
2,
1
] | [
0,
0,
0,
0,
1,
0,
1,
1,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple is correct: INTS7 (also written INTS7) is a known subunit(...TRUNCATED) | [[1.0,1.0,0.0],[1.0,1.0,0.0],[1.0,1.0,0.0],[1.0,0.0,1.0,1.0],[1.0,1.0,1.0],[0.0,0.0,0.0],[1.0,1.0,1.(...TRUNCATED) | [[4,3,1],[4,1,1],[4,3,1],[3,3,4,2],[3,1,2],[5,4,2],[1,2,1],[3,1,2],[4,4,2],[4,2,3],[5,3,2],[3,2,3,2](...TRUNCATED) | [
3,
1,
3,
3,
1,
4,
1,
1,
4,
2,
3,
2
] | ["[\n {\n \"explanation\": \"Class A (subjects that are components of the integrator complex): t(...TRUNCATED) | [
1,
1,
0,
0,
1,
0,
0,
0,
0,
0,
0,
0
] | ["","","there is no continuity for the pair (1, 2)","there is no continuity for the pair (1, 2)","",(...TRUNCATED) | 3.166667 | 12 |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 17