Triple

T9835594
Position Surface form Disambiguated ID Type / Status
Subject It Comes at Night E239091 entity
Predicate producer P490 FINISHED
Object David Kaplan E519695 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: David Kaplan | Statement: [It Comes at Night, producer, David Kaplan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Kaplan
Context triple: [It Comes at Night, producer, David Kaplan]
  • A. David Kaplan
    David Kaplan is an American philosopher best known for his influential work in the philosophy of language and logic, particularly on demonstratives, indexicals, and the semantics of context.
  • B. David Kaplan chosen
    David Kaplan is a film producer known for his work on independent and genre films, including serving as a producer on the movie "Kicks."
  • C. Jonathan Kaplan
    Jonathan Kaplan is an American film and television director best known for his work on the acclaimed 1988 courtroom drama "The Accused."
  • D. Greg Kaplan
    Greg Kaplan is an economist known for his research on household heterogeneity, consumption, and macroeconomic policy, and for his contributions to modern macroeconomic modeling.
  • E. Aaron Kaplan
    Aaron Kaplan is a television producer and executive known for developing and overseeing numerous network and cable series through his production company.
  • 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_69ca84e314108190978324a4bdb959f8 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb339aa1c8190901d8e660cef49c5 completed April 2, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1ead061388190abbed7eb29e8ea52 completed April 5, 2026, 4:53 a.m.
Created at: March 30, 2026, 8:33 p.m.