Triple

T15768787
Position Surface form Disambiguated ID Type / Status
Subject Twister E382294 entity
Predicate producer P490 FINISHED
Object Michael Crichton E224766 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: Michael Crichton | Statement: [Twister, producer, Michael Crichton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Crichton
Context triple: [Twister, producer, Michael Crichton]
  • A. Michael Crichton chosen
    Michael Crichton was an American author, screenwriter, and filmmaker best known for his science fiction and techno-thriller novels such as "Jurassic Park" and for creating the television series "ER."
  • B. John Michael Todd Crichton
    John Michael Todd Crichton is the son of the late American author and filmmaker Michael Crichton.
  • C. Kenneth Crichton
    Kenneth Crichton is a Marvel Comics character associated with the World War II-era hero Spitfire and the Union Jack legacy.
  • D. Martin Caidin
    Martin Caidin was an American author and aviation expert best known for his science fiction novel "Cyborg," which inspired the television series "The Six Million Dollar Man."
  • E. Peter Benchley
    Peter Benchley was an American author and screenwriter best known for writing the novel "Jaws," which was adapted into the iconic 1975 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e051951bac8190a7d45f3612c6de72 completed April 16, 2026, 3:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff9099335c8190b6f0fb336b3dc212 completed May 9, 2026, 7:52 p.m.
Created at: April 10, 2026, 4:47 a.m.