Triple

T5514902
Position Surface form Disambiguated ID Type / Status
Subject Dangerous E144657 entity
Predicate screenwriter P2831 FINISHED
Object Laird Doyle E134395 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: Laird Doyle | Statement: [Dangerous, screenwriter, Laird Doyle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laird Doyle
Context triple: [Dangerous, screenwriter, Laird Doyle]
  • A. Laird Doyle chosen
    Laird Doyle was an American screenwriter active in early Hollywood, known for adapting literary works for the screen.
  • B. Alexander Doyle
    Alexander Doyle was a 19th-century American sculptor known for creating prominent public monuments and statues across the United States.
  • C. Douglas McGrath
    Douglas McGrath was an American screenwriter, director, and actor known for his literary adaptations and collaborations with Woody Allen.
  • D. Kirby Doyle
    Kirby Doyle was an American poet and novelist associated with the Beat Generation and San Francisco Renaissance, known for his spontaneous, jazz-influenced verse and countercultural themes.
  • E. Chris Donlon
    Chris Donlon is a film editor known for his work on the feature film "Kicks."
  • 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_69c008f77ff88190b0cd50ca207295d1 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01f5b4e988190b590b4157cf089c1 completed March 22, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69c04cc0735881909b7ea6909570a750 completed March 22, 2026, 8:10 p.m.
Created at: March 22, 2026, 3:33 p.m.