Triple

T15064049
Position Surface form Disambiguated ID Type / Status
Subject K-19: The Widowmaker E379709 entity
Predicate producer P490 FINISHED
Object Kathryn Bigelow E54556 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: Kathryn Bigelow | Statement: [K-19: The Widowmaker, producer, Kathryn Bigelow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kathryn Bigelow
Context triple: [K-19: The Widowmaker, producer, Kathryn Bigelow]
  • A. Kathryn Bigelow chosen
    Kathryn Bigelow is an American film director and producer best known for her gritty, suspenseful dramas such as "The Hurt Locker" and "Zero Dark Thirty."
  • B. Kasi Lemmons
    Kasi Lemmons is an American film director, screenwriter, and actress known for works such as "Eve's Bayou," "Harriet," and other character-driven dramas exploring African American experiences.
  • C. Cate Shortland
    Cate Shortland is an Australian film and television director known for character-driven dramas and for directing the Marvel superhero film "Black Widow."
  • D. Sandy Powell
    Sandy Powell is a renowned British costume designer celebrated for her innovative and influential work on numerous acclaimed films.
  • E. Kathleen Marshall
    Kathleen Marshall is an American television director and producer known for her work on series such as "The Odd Couple" and "Fuller House."
  • 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_69d85cd7683881908d405c1b5d7b4f7f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dedee803ac81908bb7d66e49c2eb72 completed April 15, 2026, 12:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69febfdc8f64819083c7e3510e671b9a completed May 9, 2026, 5:02 a.m.
Created at: April 10, 2026, 3:02 a.m.