Triple

T6960048
Position Surface form Disambiguated ID Type / Status
Subject Johnny Knoxville E161345 entity
Predicate workedWith P398 FINISHED
Object Steve-O E492639 NE FINISHED

How this triple was built (2 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: Steve-O | Statement: [Johnny Knoxville, workedWith, Steve-O]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steve-O
Context triple: [Johnny Knoxville, workedWith, Steve-O]
  • A. Steve-O chosen
    Steve-O is an American stunt performer, comedian, and television personality best known for his outrageous and often dangerous pranks on the Jackass franchise.
  • B. Dr. Steve-O
    Dr. Steve-O is a reality TV series starring stunt performer Steve-O, featuring outrageous pranks and challenges in the comedic, shock-value style of the Jackass franchise.
  • C. Chris Pezman
    Chris Pezman is a collegiate sports administrator best known for serving as the athletic director of the University of Houston Cougars.
  • D. Jack Stapp
    Jack Stapp was an influential American country music executive and publisher who played a key role in shaping Nashville’s music industry and co-founding major industry institutions.
  • E. Tony Hawks
    Tony Hawks is a British comedian and author best known for his radio and television comedy work, including frequent appearances on BBC panel shows.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c68852a9a0819097797e31d492e273 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6daedbb4c8190b46846fb1265b937 completed March 27, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7589892888190bf240bdbf107efcc completed March 28, 2026, 4:27 a.m.
Created at: March 27, 2026, 2:29 p.m.