Triple

T19788310
Position Surface form Disambiguated ID Type / Status
Subject Final Cut E475335 entity
Predicate director P255 FINISHED
Object Ray Burdis 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: Ray Burdis | Statement: [Final Cut, director, Ray Burdis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ray Burdis
Context triple: [Final Cut, director, Ray Burdis]
  • A. Ray Burdis chosen
    Ray Burdis is a British actor, screenwriter, director, and film producer known for his work on gritty crime dramas and independent UK films.
  • B. Richard Burrell
    Richard Burrell is a British television producer best known for his work as an executive producer on the long-running BBC crime drama series "New Tricks."
  • C. Ray Embrey
    Ray Embrey is a well-meaning public relations consultant who helps rehabilitate the image of the troubled superhero in the film "Hancock."
  • D. Ray Cusick
    Ray Cusick was a British designer best known for creating the iconic look of the Daleks in the long-running science fiction television series Doctor Who.
  • E. Ray Fiske
    Ray Fiske is a high-powered corporate attorney and key antagonist in the legal thriller TV series "Damages."
  • 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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65389c9ac81909e61b3cbb9213e72 completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:49 p.m.