Triple

T14887855
Position Surface form Disambiguated ID Type / Status
Subject Michael John Douglas E359673 entity
Predicate workedWithDirector P19638 FINISHED
Object Tom McCarthy E344144 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: Tom McCarthy | Statement: [Michael John Douglas, workedWithDirector, Tom McCarthy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom McCarthy
Context triple: [Michael John Douglas, workedWithDirector, Tom McCarthy]
  • A. Tom McCarthy chosen
    Tom McCarthy is an American filmmaker, screenwriter, and actor best known for directing and co-writing the Academy Award–winning film "Spotlight."
  • B. Bennett Miller
    Bennett Miller is an American film director known for his critically acclaimed, character-driven dramas such as "Capote," "Moneyball," and "Foxcatcher."
  • C. Terence Winter
    Terence Winter is an American screenwriter and producer best known for his work on acclaimed television dramas such as The Sopranos and Boardwalk Empire.
  • D. Rohmer Emmanuel Baumbach
    Rohmer Emmanuel Baumbach is the son of American filmmaker Noah Baumbach and actress Greta Gerwig.
  • E. James Gray
    James Gray is an American filmmaker known for his character-driven dramas and visually rich, classical storytelling in films such as "The Lost City of Z," "Ad Astra," and "We Own the Night."
  • 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_69d827980cbc8190a0c569ae3940a1d9 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69ded5f5b1c88190815f3585770cb135 completed April 15, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b5f22c08190a9530cbd78cfc801 completed May 8, 2026, 11:01 p.m.
Created at: April 10, 2026, 2:08 a.m.