Triple

T22767796
Position Surface form Disambiguated ID Type / Status
Subject Bringing Out the Dead E563173 entity
Predicate castMember P1668 FINISHED
Object Tom Sizemore NE NERFINISHED

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: Tom Sizemore | Statement: [Bringing Out the Dead, castMember, Tom Sizemore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Sizemore
Context triple: [Bringing Out the Dead, castMember, Tom Sizemore]
  • A. Tom Sizemore chosen
    Tom Sizemore was an American character actor known for his intense supporting roles in gritty war and crime films such as "Saving Private Ryan," "Heat," and "Black Hawk Down."
  • B. Nicolas Cage
    Nicolas Cage is an American actor known for his intense and eclectic performances across action, drama, and independent films.
  • C. Darren Roy Ashmore
    Darren Roy Ashmore is a film and television producer known for his work on the documentary "Kevin Pollak's Misery Loves Comedy."
  • D. Ed Norton
    Ed Norton is the jovial, dim-witted sewer worker and best friend of Ralph Kramden in the classic American television sitcom "The Honeymooners."
  • E. Matthew Lillard
    Matthew Lillard is an American actor and director best known for his energetic, often comedic performances in films such as "Scream," "Scooby-Doo," and "Hackers."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e24552e11c81909c2d61578a558bd7 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17a81d3348190b005a43a5e03d406 completed April 29, 2026, 3:26 a.m.
Created at: April 17, 2026, 3:27 p.m.