Triple

T18475405
Position Surface form Disambiguated ID Type / Status
Subject Kevin J. O'Connor E451417 entity
Predicate notableWork P4 FINISHED
Object Widows 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: Widows | Statement: [Kevin J. O'Connor, notableWork, Widows]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Widows
Context triple: [Kevin J. O'Connor, notableWork, Widows]
  • A. Widows chosen
    Widows is a British television crime drama series, later adapted into a feature film, about a group of women who plan a heist after their criminal husbands are killed.
  • B. Widows (2018 film)
    Widows (2018 film) is a 2018 heist thriller directed by Steve McQueen that follows a group of women who plan a robbery to pay off their deceased husbands’ criminal debts.
  • C. Unnamed Widows
    Unnamed Widows are minor, individually unidentified members of the Black Widows group in the Marvel universe.
  • D. Black Widows
    The Black Widows are a covert group of highly trained female assassins and spies in the Marvel Cinematic Universe, created and controlled through the Red Room program.
  • E. Les Veuves
    Les Veuves is a French crime novel by Thomas Narcejac, known for its psychological suspense and intricate exploration of guilt and deception.
  • 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_69d8d38465a0819099b9b42d2a662ac1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e53062f67881909620c4e8fc00eb7d completed April 19, 2026, 7:43 p.m.
Created at: April 10, 2026, 11:34 a.m.