Triple

T1749368
Position Surface form Disambiguated ID Type / Status
Subject Captain Phillips E38403 entity
Predicate producer P490 FINISHED
Object Michael De Luca E165233 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 De Luca | Statement: [Captain Phillips, producer, Michael De Luca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael De Luca
Context triple: [Captain Phillips, producer, Michael De Luca]
  • A. Michael De Luca chosen
    Michael De Luca is an American film producer and studio executive known for overseeing and producing a wide range of major Hollywood films across genres.
  • B. Greg D'Auria
    Greg D'Auria is a film editor known for his work on major Hollywood productions, including the science fiction film "Star Trek Beyond."
  • C. Andrew DeLuca
    Andrew DeLuca is a fictional surgical resident and later attending surgeon on the television series Grey’s Anatomy, known for his complex personal struggles and romantic relationships with key characters.
  • D. David Della Rocco
    David Della Rocco is an American actor best known for his cult-favorite role as the eccentric sidekick in the film "The Boondock Saints."
  • E. Michael Luciano
    Michael Luciano is a film editor best known for his long collaboration with director Robert Aldrich, including work on the noir classic "Kiss Me Deadly."
  • 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_69a8862bdb2081908aefe831c8aa8017 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa63ee4d2081909dfd6d3244228c56 completed March 6, 2026, 5:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69af6529905081909bd9e7c51fc21f77 completed March 10, 2026, 12:26 a.m.
Created at: March 4, 2026, 7:31 p.m.