Triple

T15611684
Position Surface form Disambiguated ID Type / Status
Subject David McKenna E375309 entity
Predicate wroteScreenplayFor P15305 FINISHED
Object Blow E349295 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: Blow | Statement: [David McKenna, wroteScreenplayFor, Blow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blow
Context triple: [David McKenna, wroteScreenplayFor, Blow]
  • A. Blow chosen
    Blow is a 2001 crime drama film that chronicles the rise and fall of American cocaine smuggler George Jung within the 1970s–1980s drug trade.
  • B. Blow
    Blow is a track by the American heavy metal band Bastard, known for its aggressive sound and raw energy.
  • C. Blow
    "Blow" is a disco-funk inspired song by Beyoncé, known for its sensual lyrics, retro production, and vibrant roller-disco themed visuals.
  • D. Blow Out
    Blow Out is a 1981 neo-noir political thriller film directed by Brian De Palma, known for its suspenseful blend of conspiracy, sound design, and psychological tension.
  • E. Blowup
    Blowup is a 1966 mystery drama film by Michelangelo Antonioni, renowned for its exploration of perception and reality through the story of a London photographer who may have inadvertently captured a murder on film.
  • 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_69d85ccf2794819096cda4cbcb02d478 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e8148a0819087d6d69cc84487ca completed April 16, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f3913908190acdd7da62b4f521d completed May 9, 2026, 4:22 p.m.
Created at: April 10, 2026, 4:13 a.m.