Triple

T10082925
Position Surface form Disambiguated ID Type / Status
Subject Marthe Keller E213946 entity
Predicate coStarredWith P14987 FINISHED
Object William Devane E189950 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: William Devane | Statement: [Marthe Keller, coStarredWith, William Devane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Devane
Context triple: [Marthe Keller, coStarredWith, William Devane]
  • A. William Devane chosen
    William Devane is an American actor known for his intense, often authoritative roles in film and television, including prominent performances in projects like "Knots Landing" and "24."
  • B. James Dearden
    James Dearden is a British screenwriter and director best known for writing the screenplay for the hit psychological thriller film "Fatal Attraction."
  • C. Joel Harlow
    Joel Harlow is an Academy Award-winning American makeup artist and special effects designer known for his work on films such as "Star Trek" and "Pirates of the Caribbean."
  • D. Mike Morrow
    Mike Morrow is a notable individual recognized for achievements significant enough to be distinctly associated with the surname Morrow.
  • E. Griffin Dunne
    Griffin Dunne is an American actor, director, and producer known for roles in films like "An American Werewolf in London" and "After Hours."
  • 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_69ca839bf730819086900c323c9b8c95 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd04352d081908f676444cd2d2578 completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b66b256c8190861066f7c19008d2 completed April 5, 2026, 7:22 p.m.
Created at: March 30, 2026, 9 p.m.