Triple

T19982290
Position Surface form Disambiguated ID Type / Status
Subject Gemini Man E493845 entity
Predicate producer P490 FINISHED
Object Don Granger 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: Don Granger | Statement: [Gemini Man, producer, Don Granger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Don Granger
Context triple: [Gemini Man, producer, Don Granger]
  • A. Don Granger chosen
    Don Granger is an American film producer known for his work on major studio action and science fiction movies, including projects like "The Tomorrow War."
  • B. Arthur Grant
    Arthur Grant was a British cinematographer best known for his work on numerous Hammer Films productions in the mid-20th century.
  • C. Grant Grant
    Grant Grant is a fictional character best known as the parasitically infected antagonist in the horror-comedy film "Slither."
  • D. John Grono
    John Grono was a Welsh-born Australian sealer, shipbuilder, and explorer active in the early 19th century, noted for his voyages around New Zealand and the naming of several coastal features.
  • E. John Grandy
    John Grandy was a senior Royal Air Force officer who rose to become a leading commander of British fighter forces during and after the Second World War.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d13a8a88190bf5f4f697793f4c9 completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:28 p.m.