Triple

T16262127
Position Surface form Disambiguated ID Type / Status
Subject Stefan Struve E394778 entity
Predicate victoryOver P20144 FINISHED
Object Dave Herman
Dave Herman is an American mixed martial artist and UFC veteran known for his heavyweight bouts during the early 2010s.
E1204114 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Dave Herman | Statement: [Stefan Struve, victoryOver, Dave Herman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dave Herman
Context triple: [Stefan Struve, victoryOver, Dave Herman]
  • A. Matt Kaufmann
    Matt Kaufmann is a computer scientist best known for his work on automated theorem proving and the ACL2 theorem prover, often in collaboration with J Strother Moore.
  • B. Bruce Straley
    Bruce Straley is an American video game director and designer best known for his longtime work at Naughty Dog on acclaimed titles such as the Uncharted series and The Last of Us.
  • C. Gary Dourdan
    Gary Dourdan is an American actor best known for playing Warrick Brown on the television series CSI: Crime Scene Investigation.
  • D. Jim Weirich
    Jim Weirich was an influential American software developer and speaker best known in the Ruby community for his contributions to open-source tools and his work in promoting clean code practices.
  • E. Steven Bethard
    Steven Bethard is a computer scientist and natural language processing researcher known for his work on temporal information extraction, semantic role labeling, and clinical NLP.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Dave Herman
Triple: [Stefan Struve, victoryOver, Dave Herman]
Generated description
Dave Herman is an American mixed martial artist and UFC veteran known for his heavyweight bouts during the early 2010s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dave Herman
Target entity description: Dave Herman is an American mixed martial artist and UFC veteran known for his heavyweight bouts during the early 2010s.
  • A. Matt Kaufmann
    Matt Kaufmann is a computer scientist best known for his work on automated theorem proving and the ACL2 theorem prover, often in collaboration with J Strother Moore.
  • B. Bruce Straley
    Bruce Straley is an American video game director and designer best known for his longtime work at Naughty Dog on acclaimed titles such as the Uncharted series and The Last of Us.
  • C. Gary Dourdan
    Gary Dourdan is an American actor best known for playing Warrick Brown on the television series CSI: Crime Scene Investigation.
  • D. Jim Weirich
    Jim Weirich was an influential American software developer and speaker best known in the Ruby community for his contributions to open-source tools and his work in promoting clean code practices.
  • E. Steven Bethard
    Steven Bethard is a computer scientist and natural language processing researcher known for his work on temporal information extraction, semantic role labeling, and clinical NLP.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d87f221d8081909b0b2063e7528ba2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e245c4a0b08190af3574f087205afc completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0017b5f3a8819083128cf2b90cfd84 completed May 10, 2026, 5:29 a.m.
NEDg Description generation batch_6a001978fed48190963b327da30c31f0 completed May 10, 2026, 5:36 a.m.
NED2 Entity disambiguation (via description) batch_6a001a0def548190a1d800f858f3cb02 completed May 10, 2026, 5:39 a.m.
Created at: April 10, 2026, 5:04 a.m.