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 3.6k 3.81k | 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 4.09k | reasoning_paths listlengths 1 1 | paths_0 stringlengths 2 4.09k | reasoning_0 stringlengths 1.85k 5.63k | 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 48 | entity_lexical_uniqueness_0 int64 0 54 | num_triples_0 int64 0 59 | uniqueness_scores_0 listlengths 1 20 | unique_raw_response_0 listlengths 1 20 | max_uniqueness_score_0 listlengths 1 20 | factuality_scores_0 listlengths 1 20 | raw_responses_factuality_0 listlengths 1 20 | parsed_scores_factuality_0 listlengths 1 20 | raw_salience_scores_0 listlengths 1 20 | min_salience_scores_0 listlengths 1 20 | salience_raw_responses_0 listlengths 1 20 | validity_per_path_0 listlengths 1 20 | validity_reasons_0 listlengths 1 20 | avg_path_length_0 float64 0 12.6 | num_paths_0 float64 0 20 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[
"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 break down this task:\n\n1. Start entity: Morton Gould (American composer and conductor)\n2. End condition: A triple with relationship \"discography\" and tail entity \"Benny Carter discography\"\n3. I need to find as many valid paths as possible connecting these\n\nFirst, let me establish what I k... | [
"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, ... | [
2020
] | [
null
] | [
"<think>\nLet me break down this task:\n\n1. Start entity: Morton Gould (American composer and conductor)\n2. End condition: A triple with relationship \"discography\" and tail entity \"Benny Carter discography\"\n3. I need to find as many valid paths as possible connecting these\n\nFirst, let me establish what I k... | [
[
"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 victor records"], ["rca victor records", "recorded", "benny carter"], ["benny carter", "discography", "benny carter discography"]], [["morton gould", "conducted", "nbc symphony orchestra"], ["nbc symphony orchestra", "featured", "benny carter"], ["benny carter", "discography", "... | [
"<think>\nLet me break down this task:\n\n1. Start entity: Morton Gould (American composer and conductor)\n2. End condition: A triple with relationship \"discography\" and tail entity \"Benny Carter discography\"\n3. I need to find as many valid paths as possible connecting these\n\nFirst, let me establish what I k... | [[["morton gould", "recorded for", "rca victor records"], ["rca victor records", "recorded", "benny carter"], ["benny carter", "discography", "benny carter discography"]], [["morton gould", "conducted", "nbc symphony orchestra"], ["nbc symphony orchestra", "featured", "benny carter"], ["benny carter", "discography", "b... | "<think>\nLet me break down this task:\n\n1. Start entity: Morton Gould (American composer and conductor)\n2. End condition: A triple with relationship \"discography\" and tail entity \"Benny Carter discography\"\n3. I need to find as many valid paths as possible connecting these\n\nFirst, let me establish what I know:... | 0 | 0 | 0 | 0 | 11 | 9 | 16 | [
[
1,
1,
1
],
[
1,
2,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
2,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
]
] | [
"{\n \"explanation\": \"Morton Gould is publicly known as a composer and conductor; a statement that he recorded for RCA Victor Records pertains to his professional music activity and is a standard biographical detail, making it typical (T1). RCA Victor Records is a major record label, and noting that it recorded ... | [
1,
2,
1,
1,
1,
2,
1,
1
] | [
0,
0,
0,
1,
1,
0,
1,
1
] | [
"{\n \"explanation\": \"The first triple involves real entities: Morton Gould was a well‑known American composer and conductor who made recordings for the RCA Victor label, so the claim that he \\\"recorded for\\\" RCA Victor is accurate. The second triple also references real entities: RCA Victor Records is a his... | [
[
1,
1,
0
],
[
1,
0,
0
],
[
1,
1,
0
],
[
1,
1,
1
],
[
1,
1,
1
],
[
0,
1,
0
],
[
1,
1,
1
],
[
1,
1,
1
]
] | [
[
1,
1,
5
],
[
4,
3,
5
],
[
3,
1,
5
],
[
1,
1,
5
],
[
4,
3,
4
],
[
4,
3,
5
],
[
3,
1,
5
],
[
2,
2,
5
]
] | [
1,
3,
1,
1,
3,
3,
1,
2
] | [
"[\n {\n \"explanation\": \"Class A (subjects that recorded for RCA Victor Records): RCA Victor was a major label for most of the 20th century and signed thousands of artists across many genres, so we estimate roughly 5000 different subjects. Class B (objects that Morton Gould recorded for): Morton Gould was pr... | [
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 his connections to chemists.\n\nMax von Laue (1879-1960) was a German physicist known for his work on X-ray diffraction. He won the Nobel Prize in Physics in 1912.\n\nI need to find paths that:\n1. Start with \"Max von Laue\"\n2. End with a triple of the form (person, o... | [
"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... | [
1983
] | [
null
] | [
"<think>\nLet me think about Max von Laue and his connections to chemists.\n\nMax von Laue (1879-1960) was a German physicist known for his work on X-ray diffraction. He won the Nobel Prize in Physics in 1912.\n\nI need to find paths that:\n1. Start with \"Max von Laue\"\n2. End with a triple of the form (person, o... | [
[
"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", "developed", "x-ray crystallography"], ["x-ray crystallography", "applied by", "linus pauling"], ["linus pauling", "occupation", "chemist"]], [["max von laue", "developed", "x-ray diffraction"], ["x-ray diffraction", "used in", "protein structure determination"], ["protein structure determination", ... | [
"<think>\nLet me think about Max von Laue and his connections to chemists.\n\nMax von Laue (1879-1960) was a German physicist known for his work on X-ray diffraction. He won the Nobel Prize in Physics in 1912.\n\nI need to find paths that:\n1. Start with \"Max von Laue\"\n2. End with a triple of the form (person, o... | [[["max von laue", "developed", "x-ray crystallography"], ["x-ray crystallography", "applied by", "linus pauling"], ["linus pauling", "occupation", "chemist"]], [["max von laue", "developed", "x-ray diffraction"], ["x-ray diffraction", "used in", "protein structure determination"], ["protein structure determination", "... | "<think>\nLet me think about Max von Laue and his connections to chemists.\n\nMax von Laue (1879-1960) was a German physicist known for his work on X-ray diffraction. He won the Nobel Prize in Physics in 1912.\n\nI need to find paths that:\n1. Start with \"Max von Laue\"\n2. End with a triple of the form (person, occup... | 0 | 0 | 0 | 0 | 18 | 20 | 21 | [
[
1,
1,
1
],
[
1,
1,
1,
1
],
[
1,
2,
1
],
[
1,
1,
1
],
[
1,
1,
1,
1,
1
],
[
2,
2,
1,
1
],
[
1,
1,
1
],
[
1,
3,
1,
1
]
] | [
"{\n \"explanation\": \"Max von Laue is publicly known as a physicist who pioneered X‑ray diffraction, so his development of X‑ray crystallography is a core fact (T1). X‑ray crystallography’s primary purpose is structural analysis in chemistry and biology, and Linus Pauling is famously known for applying this tech... | [
1,
1,
2,
1,
1,
2,
1,
3
] | [
1,
1,
1,
1,
0,
0,
1,
0
] | [
"{\n \"explanation\": \"All three triples involve real, identifiable entities and accurate relationships. Max von Laue indeed pioneered X‑ray diffraction, which gave rise to X‑ray crystallography. Linus Pauling famously applied X‑ray crystallography in his work on chemical bonding and protein structure. Linus Paul... | [
[
1,
1,
1
],
[
1,
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
0,
1,
1,
1
],
[
1,
0,
1,
1
],
[
1,
1,
1
],
[
0,
1,
1,
1
]
] | [
[
5,
4,
1
],
[
5,
4,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
3,
4,
5,
3,
1
],
[
2,
2,
2,
1
],
[
3,
2,
1
],
[
5,
4,
1,
1
]
] | [
4,
1,
1,
1,
3,
2,
2,
1
] | [
"[\n {\n \"explanation\": \"Class A (subjects that developed X‑ray crystallography): historically Max von Laue is the primary developer, but the credit is also shared with William Lawrence Bragg, J. J. Berzelius (early ideas) and a few other early crystallographers, giving roughly 5 notable developers. Class B ... | [
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
""
] | 3.625 | 8 |
[
"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.
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 David Koechner, the American actor and comedian, and someone who was born in Newport Beach? | David Koechner | Newport Beach | place of birth | 2 | Query: What are different ways of connecting David Koechner, the American actor and comedian, and someone who was born in Newport Beach?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationship, tail) forming a c... | [
"<think>\nLet me think about connections between David Koechner (American actor and comedian) and someone born in Newport Beach.\n\nFirst, I need to identify people who were born in Newport Beach:\n- Nicole Kidman was born in Honolulu, not Newport Beach\n- Let me think... I need to find someone actually born in New... | [
"Query: What are different ways of connecting David Koechner, the American actor and comedian, and someone who was born in Newport Beach?\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, relationship, tail) form... | [
782
] | [
null
] | [
"<think>\nLet me think about connections between David Koechner (American actor and comedian) and someone born in Newport Beach.\n\nFirst, I need to identify people who were born in Newport Beach:\n- Nicole Kidman was born in Honolulu, not Newport Beach\n- Let me think... I need to find someone actually born in New... | [
[
"Twin Peaks",
"cast member",
"David Koechner"
],
[
"Twin Peaks",
"cast member",
"Rodney Rowland"
],
[
"Rodney Rowland",
"place of birth",
"Newport Beach"
]
] | [[]] | [
"<think>\nLet me think about connections between David Koechner (American actor and comedian) and someone born in Newport Beach.\n\nFirst, I need to identify people who were born in Newport Beach:\n- Nicole Kidman was born in Honolulu, not Newport Beach\n- Let me think... I need to find someone actually born in New... | [] | "<think>\nLet me think about connections between David Koechner (American actor and comedian) and someone born in Newport Beach.\n\nFirst, I need to identify people who were born in Newport Beach:\n- Nicole Kidman was born in Honolulu, not Newport Beach\n- Let me think... I need to find someone actually born in Newport... | 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 |
[
"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\nThe task is to find connection paths from:\n- Sta(...TRUNCATED) | ["Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and (...TRUNCATED) | [
1742
] | [
null
] | ["<think>\nLet me analyze this query carefully.\n\nThe task is to find connection paths from:\n- Sta(...TRUNCATED) | [["CD2AP","genetic association","Alzheimer's disease"],["ATXN7L1","genetic association","Alzheimer's(...TRUNCATED) | "[[[[\"cd2ap\", \"encoded by\", \"cd2ap gene\"], [\"cd2ap gene\", \"contains region\", \"reverse str(...TRUNCATED) | ["<think>\nLet me analyze this query carefully.\n\nThe task is to find connection paths from:\n- Sta(...TRUNCATED) | "[[[\"cd2ap\", \"encoded by\", \"cd2ap gene\"], [\"cd2ap gene\", \"contains region\", \"reverse stra(...TRUNCATED) | "\"<think>\\nLet me analyze this query carefully.\\n\\nThe task is to find connection paths from:\\n(...TRUNCATED) | 0 | 0 | 0 | 0 | 19 | 20 | 26 | [
[
1,
1,
1
],
[
1,
1,
1,
1
],
[
1,
2,
1,
1,
1
],
[
1,
1,
3,
1
],
[
1,
1,
2,
1
],
[
1,
1,
1,
2,
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/cellul(...TRUNCATED) | [
1,
1,
2,
3,
2,
2,
1,
1
] | [
1,
0,
0,
1,
1,
0,
0,
1
] | ["{\n \"explanation\": \"The first triple links the protein CD2AP (written as cd2ap) to its gene, C(...TRUNCATED) | [[1.0,1.0,1.0],[1.0,1.0,0.0,1.0],[1.0,1.0,1.0,1.0,0.0],[1.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.0,(...TRUNCATED) | [
[
5,
1,
1
],
[
4,
4,
1,
1
],
[
3,
2,
1,
1,
1
],
[
3,
4,
1,
5
],
[
1,
3,
1,
1
],
[
3,
2,
2,
1,
1
],
[
3,
4,
1,
1,
1
],
[
4,
3,
1,
1
]
] | [
1,
1,
1,
1,
1,
1,
1,
1
] | ["[\n {\n \"explanation\": \"Class A (subjects that are encoded by the cd2ap gene) – a gene ty(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1
] | ["the last triple has the same subject and object","the last triple has the same subject and object"(...TRUNCATED) | 4.25 | 8 |
[
"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 this carefully. I need to find connection paths from Kun Nong to someone(...TRUNCATED) | ["Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines?\n\nT(...TRUNCATED) | [
710
] | [
0
] | ["<think>Let me think about this carefully. I need to find connection paths from Kun Nong to someone(...TRUNCATED) | [["Kun Nong","member of","Slipknot"],["Chris Fehn","member of","Slipknot"],["Chris Fehn","place of b(...TRUNCATED) | [[]] | ["<think>Let me think about this carefully. I need to find connection paths from Kun Nong to someone(...TRUNCATED) | [] | "\"<think>Let me think about this carefully. I need to find connection paths from Kun Nong to someon(...TRUNCATED) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | [
[]
] | ["It looks like your message didn’t come through. Could you let me know what you’d like help wit(...TRUNCATED) | [
1
] | [
1
] | ["It looks like your message didn’t come through. Could you let me know how I can help you today?"(...TRUNCATED) | [
[]
] | [
[]
] | [
0
] | [
"Hello! How can I assist you today?"
] | [
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>Let me think about this carefully. I need to find connection paths from \"enfuvirtide\" to (...TRUNCATED) | ["Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a su(...TRUNCATED) | [
1704
] | [
0
] | ["<think>Let me think about this carefully. I need to find connection paths from \"enfuvirtide\" to (...TRUNCATED) | [["enfuvirtide","medical condition treated","HIV/AIDS"],["saquinavir","medical condition treated","H(...TRUNCATED) | "[[[[\"enfuvirtide\", \"treats\", \"hiv\"], [\"hiv\", \"managed with\", \"antidepressants\"], [\"ant(...TRUNCATED) | ["<think>Let me think about this carefully. I need to find connection paths from \"enfuvirtide\" to (...TRUNCATED) | "[[[\"enfuvirtide\", \"treats\", \"hiv\"], [\"hiv\", \"managed with\", \"antidepressants\"], [\"anti(...TRUNCATED) | "\"<think>Let me think about this carefully. I need to find connection paths from \\\"enfuvirtide\\\(...TRUNCATED) | 0 | 0 | 0 | 0 | 25 | 20 | 27 | [
[
1,
2,
1,
1,
1
],
[
1,
2,
1,
1,
1,
3
],
[
1,
2,
2,
3
],
[
1,
1,
1,
1
],
[
1,
1,
2,
1,
1
],
[
1,
2,
1,
1
],
[
1,
2,
2
],
[
1,
1,
1,
1
]
] | ["{\n \"explanation\": \"For the first triple, enfuvirtide is primarily known as an HIV fusion inhi(...TRUNCATED) | [
2,
2,
2,
1,
2,
2,
2,
1
] | [
0,
0,
0,
1,
0,
0,
1,
1
] | ["{\n \"explanation\": \"The first triple is correct: enfuvirtide is an FDA‑approved fusion‑inh(...TRUNCATED) | [[1.0,0.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0,1.0,0.0],[1.0,1.0,1.0,0.0],[1.0,1.0,1.0,1.0],[0.0,1.0,1.0,1.(...TRUNCATED) | [
[
4,
4,
4,
4,
3
],
[
4,
3,
4,
5,
3,
4
],
[
4,
1,
3,
3
],
[
4,
1,
2,
4
],
[
5,
3,
3,
4,
3
],
[
5,
2,
2,
3
],
[
1,
1,
3
],
[
4,
1,
1,
3
]
] | [
4,
3,
1,
1,
3,
2,
1,
1
] | ["[\n {\n \"explanation\": \"Class A (subjects that treat HIV): many antiretroviral drugs are li(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1
] | ["","the last triple has the same subject and object","the last triple has the same subject and obje(...TRUNCATED) | 4.375 | 8 |
[
"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 carefully.\n\nI need to find connection paths between:\n- Start e(...TRUNCATED) | ["Query: What are different ways of connecting Bela B, the German musician, and someone who is the u(...TRUNCATED) | [
1334
] | [
0
] | ["<think>Let me analyze this query carefully.\n\nI need to find connection paths between:\n- Start e(...TRUNCATED) | [["Bela B","member of","Die Ärzte"],["Hagen Liebing","member of","Die Ärzte"],["Hagen Liebing","un(...TRUNCATED) | "[[[[\"bela b\", \"member of\", \"die \\u00e4rzte\"], [\"die \\u00e4rzte\", \"toured with\", \"hagen(...TRUNCATED) | ["<think>Let me analyze this query carefully.\n\nI need to find connection paths between:\n- Start e(...TRUNCATED) | "[[[\"bela b\", \"member of\", \"die \\u00e4rzte\"], [\"die \\u00e4rzte\", \"toured with\", \"hagen (...TRUNCATED) | "\"<think>Let me analyze this query carefully.\\n\\nI need to find connection paths between:\\n- Sta(...TRUNCATED) | 0 | 0 | 0 | 0 | 9 | 4 | 11 | [
[
1,
1,
3
],
[
1,
3
],
[
1,
1,
3
],
[
2,
3
],
[
1,
1,
3
],
[
2,
2,
3
],
[
1,
3
]
] | ["{\n \"explanation\": \"Bela B is publicly known as a German musician and the drummer/vocalist of (...TRUNCATED) | [
1,
1,
1,
2,
1,
2,
1
] | [
0,
0,
0,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple is correct: Bela B (real German musician) is a member of (...TRUNCATED) | [
[
1,
1,
0
],
[
0,
0
],
[
1,
0,
0
],
[
0,
0
],
[
1,
1,
0
],
[
1,
1,
0
],
[
0,
0
]
] | [
[
5,
4,
5
],
[
4,
5
],
[
3,
3,
5
],
[
1,
5
],
[
1,
1,
5
],
[
1,
1,
5
],
[
4,
5
]
] | [
4,
4,
3,
1,
1,
1,
4
] | ["[\n {\n \"explanation\": \"Class A (subjects that are members of Die Ärzte): the band has thr(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
""
] | 2.571429 | 7 |
[
"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 break down this query:\n1. I need to find connection paths from \"Nicolas Chopin\" t(...TRUNCATED) | ["Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jaku(...TRUNCATED) | [
845
] | [
0
] | ["<think>Let me break down this query:\n1. I need to find connection paths from \"Nicolas Chopin\" t(...TRUNCATED) | [["Nicolas Chopin","child","Frédéric Chopin"],["Tekla Justyna Chopin","child","Frédéric Chopin"](...TRUNCATED) | [[]] | ["<think>Let me break down this query:\n1. I need to find connection paths from \"Nicolas Chopin\" t(...TRUNCATED) | [] | "\"<think>Let me break down this query:\\n1. I need to find connection paths from \\\"Nicolas Chopin(...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 |
[
"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>\nThe task is to find connection paths from \"George H. W. Bush\" (41st President) to someo(...TRUNCATED) | ["Query: What are different ways of connecting George H. W. Bush, the 41st President of the United S(...TRUNCATED) | [
1946
] | [
null
] | ["<think>\nThe task is to find connection paths from \"George H. W. Bush\" (41st President) to someo(...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>\nThe task is to find connection paths from \"George H. W. Bush\" (41st President) to someo(...TRUNCATED) | "[[[\"george h. w. bush\", \"spouse\", \"barbara bush\"], [\"barbara bush\", \"position held\", \"fi(...TRUNCATED) | "\"<think>\\nThe task is to find connection paths from \\\"George H. W. Bush\\\" (41st President) to(...TRUNCATED) | 0 | 0 | 0 | 0 | 4 | 7 | 7 | [
[
2,
1
],
[
2,
2,
1
],
[
1,
2,
1
],
[
2,
2,
1
]
] | ["{\n \"explanation\": \"George H. W. Bush is primarily known as a U.S. President and politician; h(...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
],
[
3,
5,
4
],
[
3,
5,
4
]
] | [
5,
5,
3,
3
] | ["[\n {\n \"explanation\": \"Class A (subject‑variation): all individuals x such that (x, spou(...TRUNCATED) | [
1,
1,
1,
1
] | [
"",
"",
"",
""
] | 2.75 | 4 |
[
"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 work through this step by step.\n\nThe query asks for paths connecting:\n1. Start en(...TRUNCATED) | ["Query: What are different ways of connecting INTS7, a protein involved in various cellular process(...TRUNCATED) | [
1605
] | [
0
] | ["<think>Let me work through this step by step.\n\nThe query asks for paths connecting:\n1. Start en(...TRUNCATED) | [["INTS7","genetic association","bipolar disorder"],["MCTP1","genetic association","bipolar disorder(...TRUNCATED) | "[[[[\"ints7\", \"is component of\", \"integrator complex\"], [\"integrator complex\", \"regulates t(...TRUNCATED) | ["<think>Let me work through this step by step.\n\nThe query asks for paths connecting:\n1. Start en(...TRUNCATED) | "[[[\"ints7\", \"is component of\", \"integrator complex\"], [\"integrator complex\", \"regulates tr(...TRUNCATED) | "\"<think>Let me work through this step by step.\\n\\nThe query asks for paths connecting:\\n1. Star(...TRUNCATED) | 0 | 0 | 0 | 0 | 12 | 20 | 24 | [
[
1,
1,
1
],
[
1,
1,
1,
2
],
[
1,
1,
1
],
[
1,
1,
1,
3
],
[
1,
1,
1,
1
],
[
1,
3,
1
],
[
3,
2
],
[
1,
1,
2,
1
],
[
1,
1,
1,
1
],
[
2,
1,
1
]
] | ["{\n \"explanation\": \"For each triple, I first identified the subject's core public identity. in(...TRUNCATED) | [
1,
1,
1,
1,
1,
3,
3,
2,
1,
2
] | [
0,
1,
0,
1,
0,
0,
0,
1,
1,
0
] | ["{\n \"explanation\": \"The first triple is correct: INTS7 (often written as INTS7) is a known sub(...TRUNCATED) | [[1.0,0.0,0.0],[1.0,1.0,1.0,1.0],[0.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.0,0.0,0.0],[1.0,0.0,0.0],[0.(...TRUNCATED) | [
[
4,
2,
2
],
[
4,
3,
1,
3
],
[
1,
1,
1
],
[
3,
3,
3,
3
],
[
1,
3,
2,
3
],
[
4,
4,
1
],
[
4,
1
],
[
3,
4,
2,
2
],
[
5,
3,
1,
2
],
[
2,
2,
1
]
] | [
2,
1,
1,
3,
1,
4,
4,
2,
1,
2
] | ["[\n {\n \"explanation\": \"Class A (subjects that are components of the integrator complex) in(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 3.4 | 10 |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 9