Triple

T19627754
Position Surface form Disambiguated ID Type / Status
Subject Broken Arrow E471182 entity
Predicate director P255 FINISHED
Object John Woo 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: John Woo | Statement: [Broken Arrow, director, John Woo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Woo
Context triple: [Broken Arrow, director, John Woo]
  • A. John Woo chosen
    John Woo is a renowned Hong Kong-born film director and producer best known for his highly stylized action movies featuring balletic gunplay and intense emotional drama.
  • B. John Woo Flick
    "John Woo Flick" is a gritty, hard-hitting hip-hop track by Conway the Machine known for its cinematic, gunplay-laced lyricism and classic boom-bap production.
  • C. Johnnie To
    Johnnie To is a renowned Hong Kong film director and producer known for his stylish crime thrillers and influential work in contemporary Asian cinema.
  • D. Tsui Hark
    Tsui Hark is a pioneering Hong Kong filmmaker renowned for revolutionizing the action and wuxia genres with his visually inventive, high-energy directing style.
  • E. Dennis Dun
    Dennis Dun is an American actor best known for his roles in films like "Big Trouble in Little China" and "The Last Emperor," as well as various television appearances.
  • 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640eadcc48190ab5e36ddcde0c328 completed April 20, 2026, 3:06 p.m.
Created at: April 10, 2026, 1:44 p.m.