Triple

T14398362
Position Surface form Disambiguated ID Type / Status
Subject Dirty Sexy Money E357007 entity
Predicate starring P1507 FINISHED
Object Glenn Fitzgerald E855338 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: Glenn Fitzgerald | Statement: [Dirty Sexy Money, starring, Glenn Fitzgerald]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Glenn Fitzgerald
Context triple: [Dirty Sexy Money, starring, Glenn Fitzgerald]
  • A. Glenn Fitzgerald chosen
    Glenn Fitzgerald is an American actor known for his work in independent films and television dramas, often portraying complex and introspective characters.
  • B. Jim Finley
    Jim Finley is the introspective filmmaker protagonist of Don DeLillo’s novel "Point Omega," whose desert encounter with a reclusive war intellectual drives the book’s meditative exploration of time, war, and perception.
  • C. Jim Gerald
    Jim Gerald was a French actor and comedian known for his roles in early 20th-century cinema and theater.
  • D. William Shea
    William Shea is an editor known for his work on the film "The Wedding March."
  • E. Patrick Gleason
    Patrick Gleason is an American comic book artist and writer best known for his work on DC titles such as Green Lantern Corps, Batman and Robin, and Superman.
  • 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_69d827927c988190ad98bb0360981783 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de9083f9d081908fe5c99655c410b3 completed April 14, 2026, 7:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd648409f48190b099cd137879487e completed May 8, 2026, 4:20 a.m.
Created at: April 10, 2026, 1:17 a.m.