Triple

T6204953
Position Surface form Disambiguated ID Type / Status
Subject Hugo E138723 entity
Predicate producer P490 FINISHED
Object Graham King E132899 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: Graham King | Statement: [Hugo, producer, Graham King]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Graham King
Context triple: [Hugo, producer, Graham King]
  • A. Graham King chosen
    Graham King is a British film producer known for acclaimed movies such as "The Departed," "Bohemian Rhapsody," and "The Aviator."
  • B. David Heyman
    David Heyman is a British film producer best known for originating and producing the Harry Potter film series and other major studio franchises.
  • C. Mike Donovan
    Mike Donovan is a recurring human character in Isaac Asimov’s Robot series, known as a field tester and troubleshooter who works closely with experimental robots.
  • D. Michael Hirst
    Michael Hirst is a British screenwriter and producer best known for creating the historical drama series "Vikings" and writing acclaimed historical films and television projects.
  • E. James MacDonald
    James MacDonald was an American sound effects artist and voice actor for Disney, known for providing voices and innovative audio work in many classic animated films.
  • 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_69c008acbea48190991c6b834bb45d65 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0626d96ec8190816c00c44668177d completed March 22, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c16f412d848190a8e78ad7822aa399 completed March 23, 2026, 4:50 p.m.
Created at: March 22, 2026, 4:20 p.m.