Triple

T4001907
Position Surface form Disambiguated ID Type / Status
Subject Half Baked E89432 entity
Predicate cinematography P1953 FINISHED
Object Steven Poster E82435 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: Steven Poster | Statement: [Half Baked, cinematography, Steven Poster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steven Poster
Context triple: [Half Baked, cinematography, Steven Poster]
  • A. Steven Poster chosen
    Steven Poster is an American cinematographer known for his work on films such as Donnie Darko, Rocky V, and numerous other feature and television projects.
  • B. Mark Stoermer
    Mark Stoermer is an American musician best known as the longtime bassist for the rock band The Killers.
  • C. Steven Baigelman
    Steven Baigelman is an American screenwriter and producer known for his work on biographical and crime dramas in film and television.
  • D. Philip Steuer
    Philip Steuer is a film producer best known for his work on major studio projects, including the Disney drama "Saving Mr. Banks."
  • E. Sean Hartnett
    Sean Hartnett is a relatively obscure individual whose primary distinguishing feature is sharing the surname Hartnett, with no widely recognized public profile or achievements documented.
  • 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_69aed9585e788190bec2d39deba3750f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefa4290a48190b9c8cffa012c4df1 completed March 9, 2026, 4:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b54c5e95b88190a8b5234b18d7b769 completed March 14, 2026, 11:54 a.m.
Created at: March 9, 2026, 3:34 p.m.