triple1 listlengths 3 3 | triple2 listlengths 3 3 | triple3 listlengths 3 3 | triple1_labels listlengths 3 3 | triple2_labels listlengths 3 3 | triple3_labels listlengths 3 3 | description stringlengths 8 19 | keep_triple bool 1
class | query_prompt stringlengths 3.23k 3.36k | query stringlengths 85 226 | entity_a stringlengths 3 55 | entity_b stringlengths 4 85 | rel_b stringclasses 88
values | index int64 0 930 | prompt stringlengths 3.53k 3.75k | path_prediction listlengths 1 1 | prompt_for_path listlengths 1 1 | usage listlengths 1 1 | raw_path_prediction listlengths 1 1 | source_path listlengths 3 3 | parsed_paths stringlengths 4 3.86k | reasoning_paths listlengths 1 1 | paths_0 stringlengths 2 3.86k | reasoning_0 stringlengths 1.71k 38k | 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 38 | entity_lexical_uniqueness_0 int64 0 41 | num_triples_0 int64 0 47 | uniqueness_scores_0 listlengths 1 21 | unique_raw_response_0 listlengths 1 21 | max_uniqueness_score_0 listlengths 1 21 | factuality_scores_0 listlengths 1 21 | raw_responses_factuality_0 listlengths 1 21 | parsed_scores_factuality_0 listlengths 1 21 | raw_salience_scores_0 listlengths 1 21 | min_salience_scores_0 listlengths 1 21 | salience_raw_responses_0 listlengths 1 21 | validity_per_path_0 listlengths 1 21 | validity_reasons_0 listlengths 1 21 | avg_path_length_0 float64 0 5.7 | num_paths_0 float64 0 21 | reasoning_trace stringlengths 1.71k 37.7k | len_reasoning_trace int64 1.71k 37.7k | split_reasoning_trace listlengths 1 1 | chunk_index listlengths 1 1 | entities listlengths 0 72 | relations listlengths 0 34 | num_entities int64 0 72 | num_relations int64 0 34 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[
"Q1352656",
"P166",
"Q935843"
] | [
"Q356715",
"P166",
"Q935843"
] | [
"Q356715",
"P358",
"Q100871850"
] | [
"Morton Gould",
"award received",
"Grammy Lifetime Achievement Award"
] | [
"Benny Carter",
"award received",
"Grammy Lifetime Achievement Award"
] | [
"Benny Carter",
"discography",
"Benny Carter discography"
] | Q935843__P166 | false | "Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED) | "What are different ways of connecting Morton Gould, the American composer and conductor, and someon(...TRUNCATED) | Morton Gould | Benny Carter discography | discography | 0 | "Query: What are different ways of connecting Morton Gould, the American composer and conductor, and(...TRUNCATED) | ["<think>\nOkay, I need to figure out how to connect Morton Gould, the American composer and conduct(...TRUNCATED) | ["Query: What are different ways of connecting Morton Gould, the American composer and conductor, an(...TRUNCATED) | [
{
"completion_tokens": 4930,
"prompt_tokens": 748,
"total_tokens": 5678
}
] | ["<think>\nOkay, I need to figure out how to connect Morton Gould, the American composer and conduct(...TRUNCATED) | [["Morton Gould","award received","Grammy Lifetime Achievement Award"],["Benny Carter","award receiv(...TRUNCATED) | "[[[[\"morton gould\", \"member_of\", \"ascap\"], [\"ascap\", \"member\", \"benny carter\"], [\"benn(...TRUNCATED) | ["<think>\nOkay, I need to figure out how to connect Morton Gould, the American composer and conduct(...TRUNCATED) | "[[[\"morton gould\", \"member_of\", \"ascap\"], [\"ascap\", \"member\", \"benny carter\"], [\"benny(...TRUNCATED) | "\"<think>\\nOkay, I need to figure out how to connect Morton Gould, the American composer and condu(...TRUNCATED) | 0 | 0 | 0 | 0 | 18 | 10 | 20 | [
[
1,
1,
1
],
[
3,
1,
1
],
[
1,
1,
1
],
[
2,
1,
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, conductor and pianist, so hi(...TRUNCATED) | [
1,
3,
1,
2,
1,
1,
1,
2,
1,
1
] | [
1,
0,
0,
0,
1,
0,
0,
1,
1,
0
] | ["{\n \"explanation\": \"The first triple links composer Morton Gould to ASCAP; Gould was indeed a (...TRUNCATED) | [[1.0,1.0,1.0],[0.0,1.0,1.0],[0.0,1.0,0.0],[0.0,1.0,1.0],[1.0,1.0,1.0],[1.0,0.0,1.0],[1.0,1.0,0.0],[(...TRUNCATED) | [
[
1,
1,
5
],
[
3,
3,
5
],
[
4,
3,
3
],
[
4,
4,
5
],
[
3,
3,
5
],
[
3,
4,
5
],
[
2,
2,
5
],
[
1,
1,
1
],
[
1,
1,
5
],
[
4,
4,
5
]
] | [
1,
3,
3,
4,
3,
3,
2,
1,
1,
4
] | ["[\n {\n \"explanation\": \"Class A (subject‑variation) asks for all subjects that are member(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 3 | 10 | "['<think>\\nOkay, I need to figure out how to connect Morton Gould, the American composer and condu(...TRUNCATED) | 19,752 | ["['<think>\\nOkay, I need to figure out how to connect Morton Gould, the American composer and cond(...TRUNCATED) | [
0
] | ["Morton Gould","Benny Carter","Benny Carter discography","ASCAP","BMI","RCA Victor","Columbia","Car(...TRUNCATED) | ["composed","performed","conducted","performed_at","member_of","member","recorded_for","released_rec(...TRUNCATED) | 18 | 13 |
[
"Q57067",
"P166",
"Q38104"
] | [
"Q131729",
"P166",
"Q38104"
] | [
"Q131729",
"P106",
"Q593644"
] | [
"Max von Laue",
"award received",
"Nobel Prize in Physics"
] | [
"William Lawrence Bragg",
"award received",
"Nobel Prize in Physics"
] | [
"William Lawrence Bragg",
"occupation",
"chemist"
] | Q38104__P166 | false | "Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED) | "What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffr(...TRUNCATED) | Max von Laue | chemist | occupation | 1 | "Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ra(...TRUNCATED) | ["<think>\nOkay, I need to find multiple ways to connect Max von Laue, the physicist known for X-ray(...TRUNCATED) | ["Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-r(...TRUNCATED) | [
{
"completion_tokens": 3904,
"prompt_tokens": 753,
"total_tokens": 4657
}
] | ["<think>\nOkay, I need to find multiple ways to connect Max von Laue, the physicist known for X-ray(...TRUNCATED) | [["Max von Laue","award received","Nobel Prize in Physics"],["William Lawrence Bragg","award receive(...TRUNCATED) | "[[[[\"max von laue\", \"discovered\", \"x-ray diffraction by crystals\"], [\"x-ray diffraction by c(...TRUNCATED) | ["<think>\nOkay, I need to find multiple ways to connect Max von Laue, the physicist known for X-ray(...TRUNCATED) | "[[[\"max von laue\", \"discovered\", \"x-ray diffraction by crystals\"], [\"x-ray diffraction by cr(...TRUNCATED) | "\"<think>\\nOkay, I need to find multiple ways to connect Max von Laue, the physicist known for X-r(...TRUNCATED) | 0 | 0 | 0 | 0 | 16 | 21 | 24 | [
[
1,
1,
1,
1
],
[
3,
1
],
[
2,
2,
1
],
[
1,
1,
2,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
2,
1
],
[
1,
2,
1,
1
],
[
1,
2,
1
],
[
1,
1,
1,
1
]
] | ["{\n \"explanation\": \"Each triple directly concerns the primary public identity of its subject. (...TRUNCATED) | [
1,
3,
2,
2,
1,
1,
2,
2,
2,
1
] | [
1,
0,
1,
1,
1,
1,
1,
0,
0,
1
] | ["{\n \"explanation\": \"All four triples involve real, identifiable entities and accurately descri(...TRUNCATED) | [[1.0,1.0,1.0,1.0],[0.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,1.(...TRUNCATED) | [
[
5,
4,
1,
1
],
[
4,
1
],
[
4,
4,
1
],
[
5,
5,
5,
1
],
[
2,
2,
1
],
[
1,
1,
1
],
[
5,
4,
3,
1
],
[
5,
5,
3,
1
],
[
1,
3,
1
],
[
4,
5,
1,
1
]
] | [
1,
4,
4,
5,
2,
1,
3,
3,
1,
1
] | ["[\n {\n \"explanation\": \"Class A (subjects that discovered x‑ray diffraction by crystals) (...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
0,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"there is no continuity for the pair (0, 1)",
"",
""
] | 3.4 | 10 | "['<think>\\nOkay, I need to find multiple ways to connect Max von Laue, the physicist known for X-r(...TRUNCATED) | 14,319 | ["['<think>\\nOkay, I need to find multiple ways to connect Max von Laue, the physicist known for X-(...TRUNCATED) | [
0
] | ["Max von Laue","X-ray diffraction","X-ray crystallography","Dorothy Crowfoot Hodgkin","chemist","No(...TRUNCATED) | ["discovered","contributed to","used in","used by","occupation","Nobel Prize in Physics","influenced(...TRUNCATED) | 20 | 15 |
[
"Q2085",
"P161",
"Q164328"
] | [
"Q2085",
"P161",
"Q174263"
] | [
"Q174263",
"P19",
"Q268873"
] | [
"Twin Peaks",
"cast member",
"David Koechner"
] | [
"Twin Peaks",
"cast member",
"Rodney Rowland"
] | [
"Rodney Rowland",
"place of birth",
"Newport Beach"
] | Q2085__P161 | false | "Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED) | "What are different ways of connecting David Koechner, the American actor and comedian, and someone (...TRUNCATED) | David Koechner | Newport Beach | place of birth | 2 | "Query: What are different ways of connecting David Koechner, the American actor and comedian, and s(...TRUNCATED) | ["<think>\nOkay, let's see. The user wants to connect David Koechner, the American actor and comedia(...TRUNCATED) | ["Query: What are different ways of connecting David Koechner, the American actor and comedian, and (...TRUNCATED) | [
{
"completion_tokens": 2644,
"prompt_tokens": 747,
"total_tokens": 3391
}
] | ["<think>\nOkay, let's see. The user wants to connect David Koechner, the American actor and comedia(...TRUNCATED) | [["Twin Peaks","cast member","David Koechner"],["Twin Peaks","cast member","Rodney Rowland"],["Rodne(...TRUNCATED) | "[[[[\"david koechner\", \"acted with\", \"ed helms\"], [\"ed helms\", \"place of birth\", \"newport(...TRUNCATED) | ["<think>\nOkay, let's see. The user wants to connect David Koechner, the American actor and comedia(...TRUNCATED) | "[[[\"david koechner\", \"acted with\", \"ed helms\"], [\"ed helms\", \"place of birth\", \"newport (...TRUNCATED) | "\"<think>\\nOkay, let's see. The user wants to connect David Koechner, the American actor and comed(...TRUNCATED) | 0 | 0 | 0 | 0 | 9 | 9 | 9 | [
[
1,
2
],
[
1,
1,
2
],
[
2,
2,
3
],
[
2,
1,
2
],
[
1,
1,
2
]
] | ["{\n \"explanation\": \"David Koechner is publicly known as an actor and comedian, so a fact about(...TRUNCATED) | [
1,
1,
2,
2,
1
] | [
0,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple involves real individuals, David Koechner and Ed Helms, b(...TRUNCATED) | [
[
1,
0
],
[
0,
1,
0
],
[
0,
0,
0
],
[
1,
0,
0
],
[
1,
1,
0
]
] | [
[
3,
3
],
[
4,
4,
3
],
[
2,
2,
1
],
[
1,
1,
1
],
[
2,
3,
3
]
] | [
3,
4,
2,
1,
2
] | ["[\n {\n \"explanation\": \"Class A (subjects that acted with Ed Helms): Ed Helms has appeared (...TRUNCATED) | [
1,
1,
1,
1,
1
] | [
"",
"",
"the last triple has the same subject and object",
"",
""
] | 2.8 | 5 | "['<think>\\nOkay, let\\'s see. The user wants to connect David Koechner, the American actor and com(...TRUNCATED) | 10,353 | ["['<think>\\nOkay, let\\'s see. The user wants to connect David Koechner, the American actor and co(...TRUNCATED) | [
0
] | ["David Koechner","Newport Beach","Anchorman","The Hangover","Ed Helms","Bradley Cooper","Zach Galif(...TRUNCATED) | ["acted with","worked with","directed by","produced by","member of","attended","born in","supports",(...TRUNCATED) | 32 | 16 |
[
"Q18037479",
"P2293",
"Q11081"
] | [
"Q18053558",
"P2293",
"Q11081"
] | [
"Q18053558",
"P2548",
"Q22809711"
] | [
"CD2AP",
"genetic association",
"Alzheimer's disease"
] | [
"ATXN7L1",
"genetic association",
"Alzheimer's disease"
] | [
"ATXN7L1",
"strand orientation",
"reverse strand"
] | Q11081__P2293 | false | "Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED) | "What are different ways of connecting CD2AP, a protein involved in cellular processes, and a substa(...TRUNCATED) | CD2AP | reverse strand | strand orientation | 3 | "Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and a(...TRUNCATED) | ["<think>\nOkay, let's try to figure out how to connect CD2AP to a substance with reverse strand ori(...TRUNCATED) | ["Query: What are different ways of connecting CD2AP, a protein involved in cellular processes, and (...TRUNCATED) | [
{
"completion_tokens": 3843,
"prompt_tokens": 744,
"total_tokens": 4587
}
] | ["<think>\nOkay, let's try to figure out how to connect CD2AP to a substance with reverse strand ori(...TRUNCATED) | [["CD2AP","genetic association","Alzheimer's disease"],["ATXN7L1","genetic association","Alzheimer's(...TRUNCATED) | "[[[[\"cd2ap\", \"encoded by\", \"cd2ap gene\"], [\"cd2ap gene\", \"has dna sequence\", \"cd2ap dna\(...TRUNCATED) | ["<think>\nOkay, let's try to figure out how to connect CD2AP to a substance with reverse strand ori(...TRUNCATED) | "[[[\"cd2ap\", \"encoded by\", \"cd2ap gene\"], [\"cd2ap gene\", \"has dna sequence\", \"cd2ap dna\"(...TRUNCATED) | "\"<think>\\nOkay, let's try to figure out how to connect CD2AP to a substance with reverse strand o(...TRUNCATED) | 0 | 0 | 0 | 0 | 28 | 34 | 34 | [[1,1,3],[2,1,2],[3,1,1,3],[1,1,1,1,1],[1,1,1,1],[1,2,1,1,2,1],[1,1,1,1,1,1],[2,1,1],[1,1,1,1,1],[1,(...TRUNCATED) | ["{\n \"explanation\": \"The subject 'cd2ap' is a protein, so its core domain tags are protein/gene(...TRUNCATED) | [
1,
2,
3,
1,
1,
2,
1,
2,
1,
2
] | [
0,
0,
0,
0,
0,
1,
0,
1,
1,
0
] | ["{\n \"explanation\": \"The first triple links the protein CD2AP (written as \\\"cd2ap\\\") to its(...TRUNCATED) | [[1.0,0.0,0.0],[1.0,1.0,0.0],[0.0,1.0,1.0,0.0],[1.0,1.0,1.0,1.0,0.0],[1.0,1.0,0.0,0.0],[1.0,1.0,1.0,(...TRUNCATED) | [[5,5,1],[3,2,1],[3,3,4,1],[2,4,5,1,5],[1,1,5,1],[4,4,4,3,1,1],[3,4,4,4,3,4],[1,1,1],[5,4,4,3,1],[3,(...TRUNCATED) | [
5,
2,
3,
1,
1,
1,
3,
1,
3,
1
] | ["[\n {\n \"explanation\": \"Class A (subjects that are encoded by the cd2ap gene) likely includ(...TRUNCATED) | [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
"",
"",
"",
"",
""
] | 4.4 | 10 | "['<think>\\nOkay, let\\'s try to figure out how to connect CD2AP to a substance with reverse strand(...TRUNCATED) | 13,914 | ["['<think>\\nOkay, let\\'s try to figure out how to connect CD2AP to a substance with reverse stran(...TRUNCATED) | [
0
] | ["CD2AP","CD2AP gene","reverse strand","DNA","RNA","T-cells","signaling pathway","transcription fact(...TRUNCATED) | ["encoded by","has strand orientation","strand orientation","interacts with","activates","binds to",(...TRUNCATED) | 30 | 14 |
[
"Q283572",
"P463",
"Q254138"
] | [
"Q316136",
"P463",
"Q254138"
] | [
"Q316136",
"P19",
"Q39709"
] | [
"Kun Nong",
"member of",
"Slipknot"
] | [
"Chris Fehn",
"member of",
"Slipknot"
] | [
"Chris Fehn",
"place of birth",
"Des Moines"
] | Q254138__P463 | false | "Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED) | What are different ways of connecting Kun Nong and someone who was born in Des Moines? | Kun Nong | Des Moines | place of birth | 4 | "Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines?\n\nTa(...TRUNCATED) | ["<think>\nOkay, let's tackle this problem. The user wants to connect Kun Nong to someone born in De(...TRUNCATED) | ["Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines?\n\nT(...TRUNCATED) | [
{
"completion_tokens": 1614,
"prompt_tokens": 738,
"total_tokens": 2352
}
] | ["<think>\nOkay, let's tackle this problem. The user wants to connect Kun Nong to someone born in De(...TRUNCATED) | [["Kun Nong","member of","Slipknot"],["Chris Fehn","member of","Slipknot"],["Chris Fehn","place of b(...TRUNCATED) | [[]] | ["<think>\nOkay, let's tackle this problem. The user wants to connect Kun Nong to someone born in De(...TRUNCATED) | [] | "\"<think>\\nOkay, let's tackle this problem. The user wants to connect Kun Nong to someone born in (...TRUNCATED) | 0 | 0 | 0 | 0 | 0 | 0 | 0 | [
[]
] | [
"It looks like your message didn’t come through. How can I help you today?"
] | [
1
] | [
1
] | [
"Hello! How can I assist you today?"
] | [
[]
] | [
[]
] | [
0
] | [
"Hello! How can I assist you today?"
] | [
0
] | [
""
] | 0 | 0 | "['<think>\\nOkay, let\\'s tackle this problem. The user wants to connect Kun Nong to someone born i(...TRUNCATED) | 7,359 | ["['<think>\\nOkay, let\\'s tackle this problem. The user wants to connect Kun Nong to someone born (...TRUNCATED) | [
0
] | ["Kun Nong","Mandate of Heaven","Hong Kong","China","Des Moines","Iowa","USA","The Lost Bladesman","(...TRUNCATED) | ["member of","born in","acted in","co-starred with","worked with","attended","involved in","supporte(...TRUNCATED) | 29 | 22 |
[
"Q423327",
"P2175",
"Q12199"
] | [
"Q422654",
"P2175",
"Q12199"
] | [
"Q422654",
"P769",
"Q898407"
] | [
"enfuvirtide",
"medical condition treated",
"HIV/AIDS"
] | [
"saquinavir",
"medical condition treated",
"HIV/AIDS"
] | [
"saquinavir",
"significant drug interaction",
"venlafaxine"
] | Q12199__P2175 | false | "Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED) | "What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a substance (...TRUNCATED) | enfuvirtide | venlafaxine | significant drug interaction | 5 | "Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a sub(...TRUNCATED) | ["<think>\nOkay, let's tackle this query step by step. The user wants to connect enfuvirtide, an HIV(...TRUNCATED) | ["Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a su(...TRUNCATED) | [
{
"completion_tokens": 3970,
"prompt_tokens": 759,
"total_tokens": 4729
}
] | ["<think>\nOkay, let's tackle this query step by step. The user wants to connect enfuvirtide, an HIV(...TRUNCATED) | [["enfuvirtide","medical condition treated","HIV/AIDS"],["saquinavir","medical condition treated","H(...TRUNCATED) | "[[[[\"enfuvirtide\", \"inhibits\", \"cyp3a4\"], [\"cyp3a4\", \"metabolizes\", \"venlafaxine\"], [\"(...TRUNCATED) | ["<think>\nOkay, let's tackle this query step by step. The user wants to connect enfuvirtide, an HIV(...TRUNCATED) | "[[[\"enfuvirtide\", \"inhibits\", \"cyp3a4\"], [\"cyp3a4\", \"metabolizes\", \"venlafaxine\"], [\"e(...TRUNCATED) | "\"<think>\\nOkay, let's tackle this query step by step. The user wants to connect enfuvirtide, an H(...TRUNCATED) | 0 | 0 | 0 | 0 | 9 | 6 | 10 | [
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
3,
2
],
[
1,
1,
3
]
] | ["{\n \"explanation\": \"Enfuvirtide is primarily known as an HIV fusion inhibitor drug, so its cor(...TRUNCATED) | [
1,
1,
1,
3,
1
] | [
0,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple claims that enfuvirtide inhibits the enzyme CYP3A4. While(...TRUNCATED) | [
[
0,
1,
0
],
[
0,
0,
0
],
[
0,
1,
0
],
[
1,
1,
0
],
[
1,
0,
0
]
] | [
[
3,
2,
4
],
[
2,
3,
4
],
[
2,
2,
4
],
[
4,
3,
4
],
[
4,
3,
4
]
] | [
2,
2,
2,
3,
3
] | ["[\n {\n \"explanation\": \"Class A (subjects that inhibit CYP3A4): many drugs are known CYP3A4(...TRUNCATED) | [
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
""
] | 3 | 5 | "['<think>\\nOkay, let\\'s tackle this query step by step. The user wants to connect enfuvirtide, an(...TRUNCATED) | 14,089 | ["['<think>\\nOkay, let\\'s tackle this query step by step. The user wants to connect enfuvirtide, a(...TRUNCATED) | [
0
] | ["enfuvirtide","venlafaxine","CYP3A4","P-glycoprotein","CYP2D6","CYP2C8","OATP1B1","HIV medication",(...TRUNCATED) | [
"inhibits",
"metabolizes",
"significant drug interaction",
"is metabolized by"
] | 9 | 4 |
[
"Q77462",
"P463",
"Q32645"
] | [
"Q95556",
"P463",
"Q32645"
] | [
"Q95556",
"P451",
"Q551050"
] | [
"Bela B",
"member of",
"Die Ärzte"
] | [
"Hagen Liebing",
"member of",
"Die Ärzte"
] | [
"Hagen Liebing",
"unmarried partner",
"Anja Caspary"
] | Q32645__P463 | false | "Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED) | "What are different ways of connecting Bela B, the German musician, and someone who is the unmarried(...TRUNCATED) | Bela B | Anja Caspary | unmarried partner | 6 | "Query: What are different ways of connecting Bela B, the German musician, and someone who is the un(...TRUNCATED) | ["<think>\nOkay, let's tackle this query. The user wants to connect Bela B, the German musician, to (...TRUNCATED) | ["Query: What are different ways of connecting Bela B, the German musician, and someone who is the u(...TRUNCATED) | [
{
"completion_tokens": 2204,
"prompt_tokens": 748,
"total_tokens": 2952
}
] | ["<think>\nOkay, let's tackle this query. The user wants to connect Bela B, the German musician, to (...TRUNCATED) | [["Bela B","member of","Die Ärzte"],["Hagen Liebing","member of","Die Ärzte"],["Hagen Liebing","un(...TRUNCATED) | "[[[[\"bela b\", \"member of\", \"oomph!\"], [\"oomph!\", \"collaborated with\", \"the vision bleak\(...TRUNCATED) | ["<think>\nOkay, let's tackle this query. The user wants to connect Bela B, the German musician, to (...TRUNCATED) | "[[[\"bela b\", \"member of\", \"oomph!\"], [\"oomph!\", \"collaborated with\", \"the vision bleak\"(...TRUNCATED) | "\"<think>\\nOkay, let's tackle this query. The user wants to connect Bela B, the German musician, t(...TRUNCATED) | 0 | 0 | 0 | 0 | 10 | 7 | 15 | [
[
3,
1,
3,
3
],
[
1,
1,
1,
2
],
[
1,
3,
3
],
[
3,
1,
1,
3
],
[
1,
1,
3
],
[
2,
3,
3
]
] | ["{\n \"explanation\": \"Bela B is publicly known as a German musician and drummer for Die Ärzte, (...TRUNCATED) | [
3,
1,
3,
3,
1,
3
] | [
0,
0,
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple links Bela B., a real German musician, as a member of Oom(...TRUNCATED) | [
[
0,
1,
0,
0
],
[
1,
0,
0,
0
],
[
1,
1,
0
],
[
0,
0,
0,
0
],
[
0,
0,
0
],
[
1,
0,
0
]
] | [
[
5,
4,
5,
5
],
[
4,
5,
5,
5
],
[
3,
1,
5
],
[
4,
5,
5,
5
],
[
4,
5,
5
],
[
1,
5,
5
]
] | [
4,
4,
1,
4,
4,
1
] | ["[\n {\n \"explanation\": \"Class A (subjects that are members of Oomph!): the band Oomph! has (...TRUNCATED) | [
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
"",
""
] | 3.5 | 6 | "['<think>\\nOkay, let\\'s tackle this query. The user wants to connect Bela B, the German musician,(...TRUNCATED) | 7,724 | ["['<think>\\nOkay, let\\'s tackle this query. The user wants to connect Bela B, the German musician(...TRUNCATED) | [
0
] | ["Bela B","Oomph!","The Vision Bleak","Hagen Liebing","Anja Caspary","music label","music festival",(...TRUNCATED) | ["member of","collaborator","performed at","signed to","friend","unmarried partner","band of","mutua(...TRUNCATED) | 11 | 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) | ["<think>\nOkay, let's see. The user is asking for different ways to connect Nicolas Chopin to someo(...TRUNCATED) | ["Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jaku(...TRUNCATED) | [
{
"completion_tokens": 1788,
"prompt_tokens": 748,
"total_tokens": 2536
}
] | ["<think>\nOkay, let's see. The user is asking for different ways to connect Nicolas Chopin to someo(...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) | ["<think>\nOkay, let's see. The user is asking for different ways to connect Nicolas Chopin to someo(...TRUNCATED) | "[[[\"nicolas chopin\", \"father\", \"fr\\u00e9d\\u00e9ric chopin\"], [\"fr\\u00e9d\\u00e9ric chopin(...TRUNCATED) | "\"<think>\\nOkay, let's see. The user is asking for different ways to connect Nicolas Chopin to som(...TRUNCATED) | 0 | 0 | 0 | 0 | 11 | 8 | 11 | [
[
1,
3,
2,
3
],
[
2,
3,
2,
3
],
[
2,
2,
1,
3
],
[
2,
2,
3
]
] | ["{\n \"explanation\": \"1. Nicolas Chopin is publicly known primarily as the father of the compose(...TRUNCATED) | [
3,
3,
2,
2
] | [
0,
0,
0,
0
] | ["{\n \"explanation\": \"The first triple correctly identifies Nicolas (Mikołaj) Chopin as the fat(...TRUNCATED) | [
[
1,
0,
1,
0
],
[
1,
1,
0,
0
],
[
1,
0,
1,
0
],
[
1,
0,
0
]
] | [
[
5,
5,
4,
5
],
[
1,
1,
5,
5
],
[
5,
5,
4,
5
],
[
1,
1,
5
]
] | [
4,
1,
4,
1
] | ["[\n {\n \"explanation\": \"Class A (all fathers of Frédéric Chopin): historically Frédéric(...TRUNCATED) | [
1,
1,
1,
1
] | ["the last triple has the same subject and object","the last triple has the same subject and object"(...TRUNCATED) | 3.75 | 4 | "['<think>\\nOkay, let\\'s see. The user is asking for different ways to connect Nicolas Chopin to s(...TRUNCATED) | 6,229 | ["['<think>\\nOkay, let\\'s see. The user is asking for different ways to connect Nicolas Chopin to (...TRUNCATED) | [
0
] | ["Nicolas Chopin","Frédéric Chopin","Jakub Krzyżanowski","Ludwika Chopin","Fryderyk Chopin","Izid(...TRUNCATED) | [
"father of",
"wife",
"descendant of",
"married",
"child of",
"student of"
] | 9 | 6 |
[
"Q23505",
"P40",
"Q207"
] | [
"Q190628",
"P40",
"Q207"
] | [
"Q190628",
"P39",
"Q7166256"
] | [
"George H. W. Bush",
"child",
"George W. Bush"
] | [
"Barbara Bush",
"child",
"George W. Bush"
] | [
"Barbara Bush",
"position held",
"First Lady of the United States"
] | Q207__P40 | false | "Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED) | "What are different ways of connecting George H. W. Bush, the 41st President of the United States, a(...TRUNCATED) | George H. W. Bush | First Lady of the United States | position held | 8 | "Query: What are different ways of connecting George H. W. Bush, the 41st President of the United St(...TRUNCATED) | ["<think>\nOkay, so I need to find different ways to connect George H. W. Bush to someone who was th(...TRUNCATED) | ["Query: What are different ways of connecting George H. W. Bush, the 41st President of the United S(...TRUNCATED) | [
{
"completion_tokens": 4184,
"prompt_tokens": 765,
"total_tokens": 4949
}
] | ["<think>\nOkay, so I need to find different ways to connect George H. W. Bush to someone who was th(...TRUNCATED) | [["George H. W. Bush","child","George W. Bush"],["Barbara Bush","child","George W. Bush"],["Barbara (...TRUNCATED) | "[[[[\"george h. w. bush\", \"spouse\", \"barbara bush\"], [\"barbara bush\", \"position held\", \"f(...TRUNCATED) | ["<think>\nOkay, so I need to find different ways to connect George H. W. Bush to someone who was th(...TRUNCATED) | "[[[\"george h. w. bush\", \"spouse\", \"barbara bush\"], [\"barbara bush\", \"position held\", \"fi(...TRUNCATED) | "\"<think>\\nOkay, so I need to find different ways to connect George H. W. Bush to someone who was (...TRUNCATED) | 0 | 0 | 0 | 0 | 4 | 7 | 8 | [
[
2,
1
],
[
2,
2,
1
],
[
1,
2,
1
],
[
1,
1,
1
],
[
2,
1
]
] | ["{\n \"explanation\": \"George H. W. Bush is primarily known as a U.S. President and politician. H(...TRUNCATED) | [
2,
2,
2,
1,
2
] | [
1,
1,
1,
1,
1
] | ["{\n \"explanation\": \"Both triples refer to real, well-documented individuals and relationships.(...TRUNCATED) | [
[
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1
]
] | [
[
5,
4
],
[
5,
5,
4
],
[
3,
5,
4
],
[
3,
5,
4
],
[
5,
4
]
] | [
5,
5,
3,
3,
5
] | ["[\n {\n \"explanation\": \"Class A (subjects that could be the spouse of Barbara Bush): Barbar(...TRUNCATED) | [
1,
1,
1,
1,
1
] | [
"",
"",
"",
"",
""
] | 2.6 | 5 | "['<think>\\nOkay, so I need to find different ways to connect George H. W. Bush to someone who was (...TRUNCATED) | 17,165 | ["['<think>\\nOkay, so I need to find different ways to connect George H. W. Bush to someone who was(...TRUNCATED) | [
0
] | ["George H. W. Bush","Barbara Bush","First Lady of the United States","George W. Bush","Laura Bush",(...TRUNCATED) | [
"spouse",
"position held",
"parent",
"served under",
"father-in-law"
] | 9 | 5 |
[
"Q18037778",
"P2293",
"Q131755"
] | [
"Q18046338",
"P2293",
"Q131755"
] | [
"Q18046338",
"P5572",
"Q64386"
] | [
"INTS7",
"genetic association",
"bipolar disorder"
] | [
"MCTP1",
"genetic association",
"bipolar disorder"
] | [
"MCTP1",
"expressed in",
"gallbladder"
] | Q131755__P2293 | false | "Task: Generate a Natural Language Query.\n\nYou will be given input in the following format: \nC(...TRUNCATED) | "What are different ways of connecting INTS7, a protein involved in various cellular processes, and (...TRUNCATED) | INTS7 | gallbladder | expressed in | 9 | "Query: What are different ways of connecting INTS7, a protein involved in various cellular processe(...TRUNCATED) | ["<think>\nOkay, let's tackle this query. The user wants to connect the protein INTS7 to something e(...TRUNCATED) | ["Query: What are different ways of connecting INTS7, a protein involved in various cellular process(...TRUNCATED) | [
{
"completion_tokens": 2530,
"prompt_tokens": 750,
"total_tokens": 3280
}
] | ["<think>\nOkay, let's tackle this query. The user wants to connect the protein INTS7 to something e(...TRUNCATED) | [["INTS7","genetic association","bipolar disorder"],["MCTP1","genetic association","bipolar disorder(...TRUNCATED) | "[[[[\"ints7\", \"part of\", \"integrator complex\"], [\"integrator complex\", \"regulates expressio(...TRUNCATED) | ["<think>\nOkay, let's tackle this query. The user wants to connect the protein INTS7 to something e(...TRUNCATED) | "[[[\"ints7\", \"part of\", \"integrator complex\"], [\"integrator complex\", \"regulates expression(...TRUNCATED) | "\"<think>\\nOkay, let's tackle this query. The user wants to connect the protein INTS7 to something(...TRUNCATED) | 0 | 0 | 0 | 0 | 15 | 18 | 21 | [
[
1,
3,
1
],
[
2,
1,
1
],
[
1,
1,
1
],
[
1,
3,
2
],
[
1,
3,
2
],
[
2,
1,
1
],
[
1,
1,
1
],
[
1,
2,
3,
3
],
[
1,
1,
1
],
[
1,
1,
2
]
] | ["{\n \"explanation\": \"The subject ints7 is a protein subunit of the Integrator complex, so stati(...TRUNCATED) | [
3,
2,
1,
3,
3,
2,
1,
3,
1,
1
] | [
0,
0,
1,
0,
1,
1,
0,
0,
1,
1
] | ["{\n \"explanation\": \"The first triple is correct: INTS7 (also written as ints7) is a known subu(...TRUNCATED) | [[1.0,0.0,0.0],[0.0,1.0,1.0],[1.0,1.0,1.0],[1.0,1.0,0.0],[1.0,1.0,1.0],[1.0,1.0,1.0],[0.0,1.0,0.0],[(...TRUNCATED) | [
[
4,
3,
1
],
[
3,
3,
2
],
[
4,
2,
1
],
[
4,
4,
3
],
[
3,
3,
1
],
[
3,
4,
1
],
[
3,
3,
2
],
[
4,
4,
3,
1
],
[
3,
3,
1
],
[
4,
3,
2
]
] | [
3,
3,
2,
4,
3,
3,
3,
3,
3,
3
] | ["[\n {\n \"explanation\": \"Class A (subjects that are part of the integrator complex): protein(...TRUNCATED) | [
1,
1,
1,
0,
1,
1,
1,
1,
1,
1
] | [
"",
"",
"",
"there is no continuity for the pair (1, 2)",
"",
"",
"",
"",
"",
""
] | 3.1 | 10 | "['<think>\\nOkay, let\\'s tackle this query. The user wants to connect the protein INTS7 to somethi(...TRUNCATED) | 8,146 | ["['<think>\\nOkay, let\\'s tackle this query. The user wants to connect the protein INTS7 to someth(...TRUNCATED) | [
0
] | ["INTS7","Integrator complex","RNA polymerase II","gallbladder","bile","cholangiocarcinoma","signali(...TRUNCATED) | ["part of","involved in","interacts with","regulates expression of","expressed in","associated with"(...TRUNCATED) | 25 | 8 |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 6