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 17 | keep_triple bool 1
class | query_prompt stringlengths 3.24k 3.33k | query stringlengths 86 205 | entity_a stringlengths 4 53 | entity_b stringlengths 4 66 | rel_b stringlengths 5 36 | index int64 0 921 | prompt stringlengths 3.54k 3.72k | 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 5.18k | reasoning_paths listlengths 1 1 | reasoning_0 stringlengths 4 4.18k | paths_0 stringlengths 2 5.17k | factuality_scores_0 listlengths 1 25 | raw_responses_factuality_0 listlengths 1 25 | parsed_scores_factuality_0 listlengths 1 25 | raw_salience_scores_0 listlengths 1 25 | min_salience_scores_0 listlengths 1 25 | salience_raw_responses_0 listlengths 1 25 | validity_per_path_0 listlengths 1 25 | validity_reasons_0 listlengths 1 25 | avg_path_length_0 float64 0 5.83 | num_paths_0 float64 0 25 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[
"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>\n**Evaluating collaborative paths**\n\nI’m considering a few paths related to the user’s query. First, I think about a safe route through New York City. Then there’s the Carnegie Hall option, which feels a bit risky. I’m questioning if Morton Gould worked with Benny Goodman or arranged for him, and I'm a b... | [
"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, ... | [
1837
] | [
1664
] | [
"<think>\n**Evaluating collaborative paths**\n\nI’m considering a few paths related to the user’s query. First, I think about a safe route through New York City. Then there’s the Carnegie Hall option, which feels a bit risky. I’m questioning if Morton Gould worked with Benny Goodman or arranged for him, and I'm a b... | [
[
"Morton Gould",
"award received",
"Grammy Lifetime Achievement Award"
],
[
"Benny Carter",
"award received",
"Grammy Lifetime Achievement Award"
],
[
"Benny Carter",
"discography",
"Benny Carter discography"
]
] | [[[["morton gould", "born in", "new york city"], ["new york city", "birthplace of", "benny carter"], ["benny carter", "discography", "benny carter discography"]], [["morton gould", "performed at", "carnegie hall"], ["carnegie hall", "hosted", "benny carter"], ["benny carter", "discography", "benny carter discography"]]... | [
"<think>\n**Evaluating collaborative paths**\n\nI’m considering a few paths related to the user’s query. First, I think about a safe route through New York City. Then there’s the Carnegie Hall option, which feels a bit risky. I’m questioning if Morton Gould worked with Benny Goodman or arranged for him, and I'm a b... | "<think>\n**Evaluating collaborative paths**\n\nI\u2019m considering a few paths related to the user\u2019s query. First, I think about a safe route through New York City. Then there\u2019s the Carnegie Hall option, which feels a bit risky. I\u2019m questioning if Morton Gould worked with Benny Goodman or arranged for ... | [[["morton gould", "born in", "new york city"], ["new york city", "birthplace of", "benny carter"], ["benny carter", "discography", "benny carter discography"]], [["morton gould", "performed at", "carnegie hall"], ["carnegie hall", "hosted", "benny carter"], ["benny carter", "discography", "benny carter discography"]],... | [
1,
0,
1
] | [
"{\n \"explanation\": \"The first triple states that Morton Gould was born in New York City. Both Morton Gould and New York City are real entities, and it is historically accurate that Morton Gould was born in New York City, so this triple is not hallucinated. The second triple claims that New York City is the bir... | [
[
1,
1,
1
],
[
1,
1,
0
],
[
1,
1,
1
]
] | [
[
1,
1,
3
],
[
2,
2,
3
],
[
2,
2,
2
]
] | [
1,
2,
2
] | [
"[\n {\n \"explanation\": \"For the triple ('morton gould', 'born in', 'new york city'), Class A consists of all individuals who were born in New York City. This includes a large number of people, as New York City is a major metropolitan area with a rich history of births. Class B consists of all places that Mo... | [
1,
1,
1
] | [
"",
"",
""
] | 3 | 3 |
[
"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... | [
"<answer>{\n1: [\n [\"David Koechner\", \"co-starred in\", \"Anchorman: The Legend of Ron Burgundy\"],\n [\"Anchorman: The Legend of Ron Burgundy\", \"features actor\", \"Will Ferrell\"],\n [\"Will Ferrell\", \"place of birth\", \"Newport Beach\"]\n],\n2: [\n [\"David Koechner\", \"appeared in\", \"The Office (... | [
"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... | [
1586
] | [
0
] | [
"<answer>{\n1: [\n [\"David Koechner\", \"co-starred in\", \"Anchorman: The Legend of Ron Burgundy\"],\n [\"Anchorman: The Legend of Ron Burgundy\", \"features actor\", \"Will Ferrell\"],\n [\"Will Ferrell\", \"place of birth\", \"Newport Beach\"]\n],\n2: [\n [\"David Koechner\", \"appeared in\", \"The Office (... | [
[
"Twin Peaks",
"cast member",
"David Koechner"
],
[
"Twin Peaks",
"cast member",
"Rodney Rowland"
],
[
"Rodney Rowland",
"place of birth",
"Newport Beach"
]
] | [[[["david koechner", "co-starred in", "anchorman: the legend of ron burgundy"], ["anchorman: the legend of ron burgundy", "features actor", "will ferrell"], ["will ferrell", "place of birth", "newport beach"]], [["david koechner", "appeared in", "the office (u.s.)"], ["the office (u.s.)", "guest starred", "rainn wilso... | [
null
] | null | [[["david koechner", "co-starred in", "anchorman: the legend of ron burgundy"], ["anchorman: the legend of ron burgundy", "features actor", "will ferrell"], ["will ferrell", "place of birth", "newport beach"]], [["david koechner", "appeared in", "the office (u.s.)"], ["the office (u.s.)", "guest starred", "rainn wilson... | [
0,
0,
0,
0,
0,
1,
0,
1,
0,
0,
0,
0,
0,
0,
0
] | [
"{\n \"explanation\": \"The first triple states that David Koechner co-starred in 'Anchorman: The Legend of Ron Burgundy', which is true as he is indeed part of the cast. The second triple claims that 'Anchorman: The Legend of Ron Burgundy' features Will Ferrell, which is also accurate since he plays a leading rol... | [
[
1,
1,
0
],
[
1,
1,
0
],
[
1,
1,
0
],
[
1,
1,
0
],
[
1,
1,
1,
0
],
[
1,
1,
1
],
[
1,
0,
1
],
[
1,
1,
1
],
[
1,
1,
0
],
[
1,
1,
0
],
[
1,
1,
... | [
[
4,
4,
2
],
[
2,
2,
2
],
[
3,
3,
2
],
[
3,
2,
3
],
[
4,
5,
3,
5
],
[
4,
4,
3
],
[
4,
3,
3
],
[
3,
5,
2
],
[
2,
3,
2
],
[
3,
3,
2
],
[
5,
4,
... | [
4,
2,
3,
2,
3,
4,
3,
3,
2,
3,
4,
4,
3,
2,
3
] | [
"[\n {\n \"explanation\": \"For the triple ('david koechner', 'co-starred in', 'anchorman: the legend of ron burgundy'), Class A consists of all individuals who co-starred in 'anchorman: the legend of ron burgundy'. This includes actors like Will Ferrell, Christina Applegate, and others, which could be estimate... | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 3.066667 | 15 |
[
"Q18037479",
"P2293",
"Q11081"
] | [
"Q18053558",
"P2293",
"Q11081"
] | [
"Q18053558",
"P2548",
"Q22809711"
] | [
"CD2AP",
"genetic association",
"Alzheimer's disease"
] | [
"ATXN7L1",
"genetic association",
"Alzheimer's disease"
] | [
"ATXN7L1",
"strand orientation",
"reverse strand"
] | Q11081__P2293 | false | Task: Generate a Natural Language Query.
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 CD2AP, a protein involved in cellular processes, and a substance that has a reverse strand orientation? | CD2AP | reverse strand | strand orientation | 3 | Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and a substance that has a reverse strand orientation?
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)... | [
"<think>\n**Connecting CD2AP and cDNA**\n\nI'm looking into the CD2AP gene and its potential link to Alzheimer's through APP processing. It seems that CD2AP's mRNA can be reverse-transcribed into complementary DNA (cDNA). I believe I need to use relationship strings that are concise, like \"is transcribed to\" and ... | [
"Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and a substance that has a reverse strand orientation?\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... | [
1862
] | [
1088
] | [
"<think>\n**Connecting CD2AP and cDNA**\n\nI'm looking into the CD2AP gene and its potential link to Alzheimer's through APP processing. It seems that CD2AP's mRNA can be reverse-transcribed into complementary DNA (cDNA). I believe I need to use relationship strings that are concise, like \"is transcribed to\" and ... | [
[
"CD2AP",
"genetic association",
"Alzheimer's disease"
],
[
"ATXN7L1",
"genetic association",
"Alzheimer's disease"
],
[
"ATXN7L1",
"strand orientation",
"reverse strand"
]
] | [[[["cd2ap", "encoded by", "cd2ap gene"], ["cd2ap gene", "transcribed to", "cd2ap mrna"], ["cd2ap mrna", "reverse transcribed to", "complementary dna"], ["complementary dna", "strand orientation", "reverse strand"]], [["cd2ap", "binds", "cd2 (cd2 molecule)"], ["cd2 (cd2 molecule)", "encoded by", "cd2 gene"], ["cd2 gene... | [
"<think>\n**Connecting CD2AP and cDNA**\n\nI'm looking into the CD2AP gene and its potential link to Alzheimer's through APP processing. It seems that CD2AP's mRNA can be reverse-transcribed into complementary DNA (cDNA). I believe I need to use relationship strings that are concise, like \"is transcribed to\" and ... | "<think>\n**Connecting CD2AP and cDNA**\n\nI'm looking into the CD2AP gene and its potential link to Alzheimer's through APP processing. It seems that CD2AP's mRNA can be reverse-transcribed into complementary DNA (cDNA). I believe I need to use relationship strings that are concise, like \"is transcribed to\" and \"is... | [[["cd2ap", "encoded by", "cd2ap gene"], ["cd2ap gene", "transcribed to", "cd2ap mrna"], ["cd2ap mrna", "reverse transcribed to", "complementary dna"], ["complementary dna", "strand orientation", "reverse strand"]], [["cd2ap", "binds", "cd2 (cd2 molecule)"], ["cd2 (cd2 molecule)", "encoded by", "cd2 gene"], ["cd2 gene"... | [
1,
0,
1,
0,
1,
1,
1,
1
] | [
"{\n \"explanation\": \"The first triple states that 'cd2ap' is encoded by the 'cd2ap gene'. Both 'cd2ap' and 'cd2ap gene' are real entities related to the CD2-associated protein, so this triple is not hallucinated. The second triple claims that 'cd2ap gene' is transcribed to 'cd2ap mrna'. This is a valid biologic... | [
[
1,
1,
1,
1
],
[
1,
1,
1,
0,
1
],
[
1,
1,
1,
1,
1
],
[
1,
1,
1,
1,
0,
0
],
[
1,
1,
1,
1,
1,
1
],
[
1,
1,
1,
1,
1,
1
],
[
1,
1,
1,
1,
1
],
[... | [
[
3,
3,
3,
4
],
[
5,
5,
5,
5,
5
],
[
4,
5,
5,
4,
4
],
[
3,
3,
4,
4,
4,
3
],
[
4,
5,
5,
5,
4,
4
],
[
4,
1,
1,
3,
4,
5
],
[
4,
5,
5,
5,
4
],
[... | [
3,
5,
4,
3,
4,
1,
4,
2
] | [
"[\n {\n \"explanation\": \"For the triple ('cd2ap', 'encoded by', 'cd2ap gene'), Class A consists of all subjects that can be encoded by the 'cd2ap gene'. This includes various proteins or molecules that could be produced by this gene, which is a relatively small set. Class B consists of all objects that can e... | [
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"the last triple has the same subject and object"
] | 5.25 | 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) | ["<answer>{\n1: [\n [\"Kun Nong\", \"coauthored\", \"Bill Bryson\"],\n [\"Bill Bryson\", \"place o(...TRUNCATED) | ["Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines?\n\nT(...TRUNCATED) | [
1787
] | [
0
] | ["<answer>{\n1: [\n [\"Kun Nong\", \"coauthored\", \"Bill Bryson\"],\n [\"Bill Bryson\", \"place o(...TRUNCATED) | [["Kun Nong","member of","Slipknot"],["Chris Fehn","member of","Slipknot"],["Chris Fehn","place of b(...TRUNCATED) | "[[[[\"kun nong\", \"coauthored\", \"bill bryson\"], [\"bill bryson\", \"place of birth\", \"des moi(...TRUNCATED) | [
null
] | null | "[[[\"kun nong\", \"coauthored\", \"bill bryson\"], [\"bill bryson\", \"place of birth\", \"des moin(...TRUNCATED) | [
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple ('kun nong', 'coauthored', 'bill bryson') is marked as ha(...TRUNCATED) | [[0.0,1.0],[0.0,1.0],[0.0,0.0,1.0],[0.0,1.0,1.0],[0.0,0.0,1.0],[0.0,0.0,1.0],[0.0,1.0,0.0,1.0],[0.0,(...TRUNCATED) | [[4,1],[4,1],[3,3,1],[1,1,1],[5,4,3],[5,4,1],[4,3,3,1],[5,5,3],[2,2,2],[4,3,2],[3,3,1],[3,3,1],[3,2](...TRUNCATED) | [
4,
4,
3,
1,
4,
4,
3,
5,
2,
3,
3,
3,
3,
1,
3,
3,
3,
3,
2,
2
] | ["[\n {\n \"explanation\": \"For the triple ('kun nong', 'coauthored', 'bill bryson'), Class A i(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 2.9 | 20 |
[
"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>\n\n</think>\n\n<answer>{\n1: [\n[\"enfuvirtide\", \"brand name\", \"Fuzeon\"],\n[\"Fuzeon\(...TRUNCATED) | ["Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a su(...TRUNCATED) | [
2315
] | [
1664
] | ["<think>\n\n</think>\n\n<answer>{\n1: [\n[\"enfuvirtide\", \"brand name\", \"Fuzeon\"],\n[\"Fuzeon\(...TRUNCATED) | [["enfuvirtide","medical condition treated","HIV/AIDS"],["saquinavir","medical condition treated","H(...TRUNCATED) | "[[[[\"enfuvirtide\", \"brand name\", \"fuzeon\"], [\"fuzeon\", \"developed by\", \"trimeris\"], [\"(...TRUNCATED) | [
"<think>\n\n"
] | "<think>\n\n" | "[[[\"enfuvirtide\", \"brand name\", \"fuzeon\"], [\"fuzeon\", \"developed by\", \"trimeris\"], [\"t(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1
] | ["{\n \"explanation\": \"The evaluation of the triples reveals the following: The first triple iden(...TRUNCATED) | [[1.0,1.0,1.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0,1.(...TRUNCATED) | [
[
5,
5,
5,
4,
4,
4
],
[
3,
3,
3,
4
],
[
4,
4,
3,
2,
2,
3
],
[
1,
1,
3
],
[
4,
3,
3,
3
],
[
3,
3,
3,
3
],
[
5,
4,
4,
4
],
[
2,
2,
4
]
] | [
4,
3,
2,
1,
3,
3,
4,
2
] | ["[\n {\n \"explanation\": \"For the triple ('enfuvirtide', 'brand name', 'fuzeon'), Class A con(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
""
] | 4.25 | 8 |
[
"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) | ["<answer>{\n1: [\n[\"Nicolas Chopin\", \"father\", \"Frédéric Chopin\"],\n[\"Frédéric Chopin\",(...TRUNCATED) | ["Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jaku(...TRUNCATED) | [
1522
] | [
0
] | ["<answer>{\n1: [\n[\"Nicolas Chopin\", \"father\", \"Frédéric Chopin\"],\n[\"Frédéric Chopin\",(...TRUNCATED) | [["Nicolas Chopin","child","Frédéric Chopin"],["Tekla Justyna Chopin","child","Frédéric Chopin"](...TRUNCATED) | "[[[[\"nicolas chopin\", \"father\", \"fr\\u00e9d\\u00e9ric chopin\"], [\"fr\\u00e9d\\u00e9ric chopi(...TRUNCATED) | [
null
] | null | "[[[\"nicolas chopin\", \"father\", \"fr\\u00e9d\\u00e9ric chopin\"], [\"fr\\u00e9d\\u00e9ric chopin(...TRUNCATED) | [
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple states that 'nicolas chopin' is the father of 'frédéric(...TRUNCATED) | [[1.0,1.0,0.0],[0.0,0.0,0.0],[0.0,0.0,0.0],[0.0,1.0,0.0],[1.0,0.0,0.0],[1.0,0.0,0.0],[1.0,0.0,0.0],[(...TRUNCATED) | [
[
5,
5,
5
],
[
4,
3,
5
],
[
1,
1,
5
],
[
3,
4,
5
],
[
3,
3,
5
],
[
2,
2,
5
],
[
5,
4,
5
],
[
2,
2,
5
],
[
2,
1,
5
],
[
4,
3,
5
],
[
4,
3,
5
],... | [
5,
3,
1,
3,
3,
2,
4,
2,
1,
3,
3,
3
] | ["[\n {\n \"explanation\": \"For the triple ('nicolas chopin', 'father', 'frédéric chopin'), C(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 3 | 12 |
[
"Q16727447",
"P54",
"Q223522"
] | [
"Q5293277",
"P54",
"Q223522"
] | [
"Q5293277",
"P69",
"Q235034"
] | [
"Horace Belton",
"member of sports team",
"Kansas City Chiefs"
] | [
"Don Parrish",
"member of sports team",
"Kansas City Chiefs"
] | [
"Don Parrish",
"educated at",
"University of Pittsburgh"
] | Q223522__P54 | 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 Horace Belton and someone who was educated at the University (...TRUNCATED) | Horace Belton | University of Pittsburgh | educated at | 13 | "Query: What are different ways of connecting Horace Belton and someone who was educated at the Univ(...TRUNCATED) | ["<think>\n**Exploring connections through football paths**\n\nI'm considering how to create various(...TRUNCATED) | ["Query: What are different ways of connecting Horace Belton and someone who was educated at the Uni(...TRUNCATED) | [
2974
] | [
2048
] | ["<think>\n**Exploring connections through football paths**\n\nI'm considering how to create various(...TRUNCATED) | [["Horace Belton","member of sports team","Kansas City Chiefs"],["Don Parrish","member of sports tea(...TRUNCATED) | "[[[[\"horace belton\", \"played for\", \"kansas city chiefs\"], [\"kansas city chiefs\", \"member o(...TRUNCATED) | ["<think>\n**Exploring connections through football paths**\n\nI'm considering how to create various(...TRUNCATED) | "\"<think>\\n**Exploring connections through football paths**\\n\\nI'm considering how to create var(...TRUNCATED) | "[[[\"horace belton\", \"played for\", \"kansas city chiefs\"], [\"kansas city chiefs\", \"member of(...TRUNCATED) | [
0,
0,
0,
0,
0,
0,
1,
0,
0,
0,
0,
1
] | ["{\n \"explanation\": \"The first triple states that Horace Belton played for the Kansas City Chie(...TRUNCATED) | [[0.0,1.0,0.0,1.0],[0.0,1.0,1.0,1.0],[0.0,1.0,1.0,1.0],[0.0,1.0,1.0,1.0],[0.0,1.0,1.0,1.0],[0.0,1.0,(...TRUNCATED) | [[3,4,2,2],[3,4,2,1],[3,3,3,1],[3,3,3,1],[3,4,2,1],[3,4,2,1],[3,5,5,2,1],[2,4,4,2,1],[3,4,4,3,1],[3,(...TRUNCATED) | [
2,
2,
3,
3,
2,
2,
2,
2,
3,
3,
2,
3
] | ["[\n {\n \"explanation\": \"For the triple ('horace belton', 'played for', 'kansas city chiefs'(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 4.25 | 12 |
[
"Q319392",
"P463",
"Q43267"
] | [
"Q2831",
"P463",
"Q43267"
] | [
"Q2831",
"P8693",
"Q74073658"
] | [
"Marlon Jackson",
"member of",
"The Jackson 5"
] | [
"Michael Jackson",
"member of",
"The Jackson 5"
] | [
"Michael Jackson",
"fandom",
"Michael Jackson fandom"
] | Q43267__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 Marlon Jackson, a member of the famous Jackson family, and so(...TRUNCATED) | Marlon Jackson | Michael Jackson fandom | fandom | 15 | "Query: What are different ways of connecting Marlon Jackson, a member of the famous Jackson family,(...TRUNCATED) | ["<think>\nI need to return JSON with integer keys starting from 1, which is straightforward enough!(...TRUNCATED) | ["Query: What are different ways of connecting Marlon Jackson, a member of the famous Jackson family(...TRUNCATED) | [
1339
] | [
576
] | ["<think>\nI need to return JSON with integer keys starting from 1, which is straightforward enough!(...TRUNCATED) | [["Marlon Jackson","member of","The Jackson 5"],["Michael Jackson","member of","The Jackson 5"],["Mi(...TRUNCATED) | "[[[[\"marlon jackson\", \"brother of\", \"michael jackson\"], [\"michael jackson\", \"fandom\", \"m(...TRUNCATED) | ["<think>\nI need to return JSON with integer keys starting from 1, which is straightforward enough!(...TRUNCATED) | "\"<think>\\nI need to return JSON with integer keys starting from 1, which is straightforward enoug(...TRUNCATED) | "[[[\"marlon jackson\", \"brother of\", \"michael jackson\"], [\"michael jackson\", \"fandom\", \"mi(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | ["{\n \"explanation\": \"The first triple states that Marlon Jackson is the brother of Michael Jack(...TRUNCATED) | [[1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0],[1.0,(...TRUNCATED) | [[5,1],[5,5,1],[5,5,1],[5,5,1],[2,2,1],[3,4,1],[4,4,1],[4,3,2],[4,3,1],[5,5,1],[3,3,4,1],[2,5,1],[5,(...TRUNCATED) | [
5,
5,
5,
5,
2,
3,
4,
3,
3,
5,
3,
2,
3,
3,
3
] | ["[\n {\n \"explanation\": \"For the triple ('marlon jackson', 'brother of', 'michael jackson'),(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 3 | 15 |
[
"Q1257",
"P39",
"Q81066"
] | [
"Q1267",
"P39",
"Q81066"
] | [
"Q1267",
"P106",
"Q49757"
] | [
"Boutros Boutros-Ghali",
"position held",
"United Nations Secretary-General"
] | [
"Dag Hammarskjöld",
"position held",
"United Nations Secretary-General"
] | [
"Dag Hammarskjöld",
"occupation",
"poet"
] | Q81066__P39 | 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 Boutros Boutros-Ghali, the former Secretary-General of the Un(...TRUNCATED) | Boutros Boutros-Ghali | poet | occupation | 16 | "Query: What are different ways of connecting Boutros Boutros-Ghali, the former Secretary-General of(...TRUNCATED) | ["<think>\n\n</think>\n\n<answer>{\n1: [\n[\"Boutros Boutros-Ghali\", \"office\", \"United Nations\"(...TRUNCATED) | ["Query: What are different ways of connecting Boutros Boutros-Ghali, the former Secretary-General o(...TRUNCATED) | [
3007
] | [
2112
] | ["<think>\n\n</think>\n\n<answer>{\n1: [\n[\"Boutros Boutros-Ghali\", \"office\", \"United Nations\"(...TRUNCATED) | [["Boutros Boutros-Ghali","position held","United Nations Secretary-General"],["Dag Hammarskjöld","(...TRUNCATED) | "[[[[\"boutros boutros-ghali\", \"office\", \"united nations\"], [\"united nations\", \"member state(...TRUNCATED) | [
"<think>\n\n"
] | "<think>\n\n" | "[[[\"boutros boutros-ghali\", \"office\", \"united nations\"], [\"united nations\", \"member state\(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
0,
1,
1,
1,
1,
1
] | ["{\n \"explanation\": \"The first triple states that Boutros Boutros-Ghali held an office at the U(...TRUNCATED) | [[1.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.0,(...TRUNCATED) | [[3,3,1,1],[3,3,1,1],[2,3,1,1],[2,3,1,1],[3,3,1,1],[3,3,1,1],[2,3,1,1],[4,3,1,1],[2,3,1,1],[4,3,1,1](...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
3,
1,
1,
1
] | ["[\n {\n \"explanation\": \"For the triple ('boutros boutros-ghali', 'office', 'united nations'(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 3.933333 | 15 |
[
"Q104776463",
"P58",
"Q107809789"
] | [
"Q104776463",
"P58",
"Q1904757"
] | [
"Q1904757",
"P106",
"Q33999"
] | [
"The Expedition of the Family Fox",
"screenwriter",
"Job Römer"
] | [
"The Expedition of the Family Fox",
"screenwriter",
"Nienke Römer"
] | [
"Nienke Römer",
"occupation",
"actor"
] | Q104776463__P58 | 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 Job Römer, a notable figure, and someone who is an actor? | Job Römer | actor | occupation | 18 | "Query: What are different ways of connecting Job Römer, a notable figure, and someone who is an ac(...TRUNCATED) | ["<answer>{\n1: [\n[\"Job Römer\", \"authored\", \"Book: The Maastricht Years\"],\n[\"Book: The Maa(...TRUNCATED) | ["Query: What are different ways of connecting Job Römer, a notable figure, and someone who is an a(...TRUNCATED) | [
1269
] | [
0
] | ["<answer>{\n1: [\n[\"Job Römer\", \"authored\", \"Book: The Maastricht Years\"],\n[\"Book: The Maa(...TRUNCATED) | [["The Expedition of the Family Fox","screenwriter","Job Römer"],["The Expedition of the Family Fox(...TRUNCATED) | "[[[[\"job r\\u00f6mer\", \"authored\", \"book: the maastricht years\"], [\"book: the maastricht yea(...TRUNCATED) | [
null
] | null | "[[[\"job r\\u00f6mer\", \"authored\", \"book: the maastricht years\"], [\"book: the maastricht year(...TRUNCATED) | [
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
1,
0,
1
] | ["{\n \"explanation\": \"The first triple states that 'job römer' authored 'book: the maastricht y(...TRUNCATED) | [[0.0,0.0,0.0,1.0],[1.0,0.0,0.0,1.0],[0.0,1.0,0.0,1.0],[0.0,1.0,0.0,1.0],[1.0,0.0,1.0],[0.0,0.0,0.0,(...TRUNCATED) | [[5,4,4,2],[4,3,4,1],[3,3,3,1],[3,4,4,1],[4,4,1],[5,5,5,2],[4,3,1],[3,3,1],[3,4,1],[3,4,1],[4,3,2],[(...TRUNCATED) | [
4,
3,
3,
3,
4,
5,
3,
3,
3,
3,
3,
3,
3,
3,
3
] | ["[\n {\n \"explanation\": \"For the triple ('job römer', 'authored', 'book: the maastricht yea(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 3.4 | 15 |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 26