triple1 listlengths 3 3 | triple2 listlengths 3 3 | triple3 listlengths 3 3 | triple1_labels listlengths 3 3 | triple2_labels listlengths 3 3 | triple3_labels listlengths 3 3 | description stringlengths 8 19 | keep_triple bool 1
class | query_prompt stringlengths 3.23k 3.36k | query stringlengths 85 226 | entity_a stringlengths 3 55 | entity_b stringlengths 4 85 | rel_b stringclasses 88
values | index int64 0 930 | prompt stringlengths 3.53k 3.75k | path_prediction listlengths 1 1 | prompt_for_path listlengths 1 1 | all_response_tokens listlengths 1 1 | all_reasoning_tokens listlengths 1 1 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[
"Q1352656",
"P166",
"Q935843"
] | [
"Q356715",
"P166",
"Q935843"
] | [
"Q356715",
"P358",
"Q100871850"
] | [
"Morton Gould",
"award received",
"Grammy Lifetime Achievement Award"
] | [
"Benny Carter",
"award received",
"Grammy Lifetime Achievement Award"
] | [
"Benny Carter",
"discography",
"Benny Carter discography"
] | Q935843__P166 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry? | Morton Gould | Benny Carter discography | discography | 0 | Query: What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relatio... | [
"<think>\nLet me analyze this query carefully. I need to find connection paths from \"Morton Gould\" (American composer and conductor) to \"Benny Carter discography\" (the discography of Benny Carter, who has a notable discography in music).\n\nThe paths must:\n1. Start with Morton Gould\n2. End with a triple where... | [
"Query: What are different ways of connecting Morton Gould, the American composer and conductor, and someone who has a notable discography in the music industry?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, ... | [
2037
] | [
null
] |
[
"Q57067",
"P166",
"Q38104"
] | [
"Q131729",
"P166",
"Q38104"
] | [
"Q131729",
"P106",
"Q593644"
] | [
"Max von Laue",
"award received",
"Nobel Prize in Physics"
] | [
"William Lawrence Bragg",
"award received",
"Nobel Prize in Physics"
] | [
"William Lawrence Bragg",
"occupation",
"chemist"
] | Q38104__P166 | false | Task: Generate a Natural Language Query.
You will be given input in the following format:
Concept A: entity1
Concept B: entity2
Concept C: (concept B, rel, entity3)
Concept A and Concept C are connected via an independent concept B. Concept C is a property of Concept B, which the person is supposed to guess.
You... | What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist? | Max von Laue | chemist | occupation | 1 | Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual t... | [
"<think>\nLet me think about Max von Laue and how he might connect to chemists.\n\nMax von Laue was a German physicist (1879-1960) who won the Nobel Prize in Physics in 1912 for his work on X-ray diffraction. \n\nTo find connections between Max von Laue and chemists, I need to think about:\n1. People he directly kn... | [
"Query: What are different ways of connecting Max von Laue, the physicist known for his work in X-ray diffraction, and someone who is recognized for their contributions as a chemist?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of fa... | [
2514
] | [
null
] |
[
"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>\nI need to find connection paths between David Koechner and someone born in Newport Beach.\n\nFirst, let me identify who David Koechner is:\n- David Koechner is an American actor and comedian known for roles in films and TV shows like Anchorman, The Office, etc.\n\nNow I need to find people or entities con... | [
"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... | [
919
] | [
null
] |
[
"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>\nLet me analyze this query carefully:\n\n1. Start entity: CD2AP (a protein involved in cellular processes)\n2. End condition: A path that ends with a triple whose relationship is \"strand orientation\" and whose tail is \"reverse strand\"\n3. Need to find many connection paths between these two\n\nFirst, l... | [
"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... | [
2142
] | [
null
] |
[
"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.
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 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?
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 continuous chain that begins with one entity... | [
"<think>\nI need to find connection paths between \"Kun Nong\" and someone born in Des Moines.\n\nFirst, let me think about who Kun Nong is. Kun Nong is a Chinese film and television actress. I need to find paths that connect her to people born in Des Moines.\n\nThe target is to end with a triple of the form (perso... | [
"Query: What are different ways of connecting Kun Nong and someone who was born in Des Moines?\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) forming a continuous chain that begins with one... | [
980
] | [
null
] |
[
"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.
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 enfuvirtide, a medication used to treat HIV, and a substance that has a significant drug interaction with venlafaxine? | enfuvirtide | venlafaxine | significant drug interaction | 5 | Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a substance that has a significant drug interaction with venlafaxine?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, rela... | [
"<think>\nLet me analyze this query systematically.\n\nThe query asks for connection paths from:\n- Start entity: \"enfuvirtide\" (an HIV medication)\n- End condition: A triple with relationship \"significant drug interaction\" and tail entity \"venlafaxine\" (an antidepressant)\n\nSo I need to find paths that:\n1.... | [
"Query: What are different ways of connecting enfuvirtide, a medication used to treat HIV, and a substance that has a significant drug interaction with venlafaxine?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (hea... | [
2262
] | [
null
] |
[
"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.
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 Bela B, the German musician, and someone who is the unmarried partner of Hagen Liebing? | Bela B | Anja Caspary | unmarried partner | 6 | Query: What are different ways of connecting Bela B, the German musician, and someone who is the unmarried partner of Hagen Liebing?
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 conti... | [
"<think>\nLet me work through this step-by-step.\n\nI need to find connection paths from \"Bela B\" (German musician) to someone who is the unmarried partner of \"Hagen Liebing\".\n\nFirst, let me establish what I know:\n- Bela B is a German musician, member of the band Die Ärzte\n- I need to find who is the unmarr... | [
"Query: What are different ways of connecting Bela B, the German musician, and someone who is the unmarried partner of Hagen Liebing?\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) forming ... | [
555
] | [
null
] |
[
"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.
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 Nicolas Chopin, and someone who is the father of Jakub Krzyżanowski? | Nicolas Chopin | Jakub Krzyżanowski | father | 7 | Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jakub Krzyżanowski?
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 continuous chain that be... | [
"<think>\nLet me analyze this query carefully.\n\nI need to find connection paths from \"Nicolas Chopin\" to \"someone who is the father of Jakub Krzyżanowski\".\n\nFirst, let me identify the key entities:\n1. Nicolas Chopin - I need to identify who this is\n2. Jakub Krzyżanowski - I need to find who his father is\... | [
"Query: What are different ways of connecting Nicolas Chopin, and someone who is the father of Jakub Krzyżanowski?\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) forming a continuous chain ... | [
796
] | [
null
] |
[
"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.
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 George H. W. Bush, the 41st President of the United States, and someone who held the position of First Lady of the United States? | 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 States, and someone who held the position of First Lady of the United States?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples ... | [
"<think>\nLet me think about how to connect George H. W. Bush (41st President) to someone who held the position of First Lady of the United States.\n\nFirst, let me identify who would be First Ladies:\n- Barbara Bush (George H. W. Bush's wife) - First Lady 1989-1993\n- Laura Bush (George W. Bush's wife) - First Lad... | [
"Query: What are different ways of connecting George H. W. Bush, the 41st President of the United States, and someone who held the position of First Lady of the United States?\n\nTask: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual t... | [
1619
] | [
null
] |
[
"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.
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 INTS7, a protein involved in various cellular processes, and a substance that is expressed in the gallbladder? | INTS7 | gallbladder | expressed in | 9 | Query: What are different ways of connecting INTS7, a protein involved in various cellular processes, and a substance that is expressed in the gallbladder?
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... | [
"<think>\nThis is a challenging task because I need to find connection paths from INTS7 (a protein) to something \"expressed in gallbladder\".\n\nLet me think about what I know:\n1. INTS7 is a protein that is part of the INT (Integrator) complex, involved in various cellular processes including transcription and DN... | [
"Query: What are different ways of connecting INTS7, a protein involved in various cellular processes, and a substance that is expressed in the gallbladder?\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, relat... | [
1135
] | [
null
] |
[
"Q47703",
"P161",
"Q960676"
] | [
"Q47703",
"P161",
"Q786720"
] | [
"Q786720",
"P19",
"Q18419"
] | [
"The Godfather",
"cast member",
"Joe Spinell"
] | [
"The Godfather",
"cast member",
"Richard Bright"
] | [
"Richard Bright",
"place of birth",
"Brooklyn"
] | Q47703__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 Joe Spinell, the American actor, and someone who was born in Brooklyn? | Joe Spinell | Brooklyn | place of birth | 10 | Query: What are different ways of connecting Joe Spinell, the American actor, and someone who was born in Brooklyn?
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 continuous chain that ... | [
"<think>\nLet me think about Joe Spinell and connections to someone born in Brooklyn.\n\nFirst, I need to establish what I know about Joe Spinell:\n- Joe Spinell was an American actor\n- He was born in 1956 (I believe)\n- He appeared in various films and TV shows\n\nWait, let me reconsider. There may be multiple Jo... | [
"Query: What are different ways of connecting Joe Spinell, the American actor, and someone who was born in Brooklyn?\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) forming a continuous chai... | [
1679
] | [
null
] |
[
"Q315199",
"P463",
"Q254138"
] | [
"Q3116290",
"P463",
"Q254138"
] | [
"Q3116290",
"P106",
"Q4351403"
] | [
"Mick Thomson",
"member of",
"Slipknot"
] | [
"Greg Welts",
"member of",
"Slipknot"
] | [
"Greg Welts",
"occupation",
"percussionist"
] | Q254138__P463 | 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 Mick Thomson, the guitarist known for his work in heavy metal, and someone who is a percussionist by occupation? | Mick Thomson | percussionist | occupation | 11 | Query: What are different ways of connecting Mick Thomson, the guitarist known for his work in heavy metal, and someone who is a percussionist by occupation?
Task: Identify how two real-world entities are connected by producing MANY connection paths. A connection path is a sequence of factual triples (head, relationsh... | [
"<think>\nLet me analyze this query step by step.\n\nThe task is to find connection paths between:\n- Start entity: Mick Thomson (guitarist in heavy metal)\n- End condition: A triple with relationship \"occupation\" and tail \"percussionist\"\n\nMick Thomson is the guitarist for Slipknot, a heavy metal/nu metal ban... | [
"Query: What are different ways of connecting Mick Thomson, the guitarist known for his work in heavy metal, and someone who is a percussionist by occupation?\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, rel... | [
1587
] | [
null
] |
End of preview. Expand in Data Studio
Dataset: connections-dev/connection_queries_jan12
This dataset was generated using the inference script with the following configuration:
Inference Parameters
Model Configuration
- Model Name:
claude-haiku-4-5-20251001 - Server URL:
Not specified - API Key:
Not provided - Request Timeout:
30 seconds
Query Configuration
- Query Type:
natural - Query Column:
query - Sampling Type:
original
Generation Parameters
- Temperature:
0.7 - Max Tokens:
4096 - Number of Runs:
1 - Chunk Size:
Entire dataset - Effort Level:
medium
Feature Flags
- Step by Step Reasoning:
False - Reasoning Enabled:
False - No Curator:
False - Index Filter:
None (all samples)
Data Information
- Input File:
connections-dev/connection_queries_jan12 - Number of Samples:
931 - Output Filename:
connection_queries_jan12__natural__original__1__medium__0.7__4096__claude-haiku-4-5-20251001.jsonl
Dataset Structure
The dataset contains the following key columns:
query: The original queryentity_a: Starting entityentity_b: Target entityrel_b: Target relationshippath_prediction: Generated connection pathsprompt_for_path: Prompts used for path generation
Usage
You can load this dataset using:
from datasets import load_dataset
dataset = load_dataset("connections-dev/connection_queries_jan12_natural_original_1_medium_0.7_4096_claude-haiku-4-5-20251001")
Generation Details
This dataset was generated on 2026-01-12 23:27:30 using the inference pipeline with the above configuration.
- Downloads last month
- 12