Triple

T12424727
Position Surface form Disambiguated ID Type / Status
Subject The Formula E296867 entity
Predicate starring P1507 FINISHED
Object G. D. Spradlin E823721 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: G. D. Spradlin | Statement: [The Formula, starring, G. D. Spradlin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: G. D. Spradlin
Context triple: [The Formula, starring, G. D. Spradlin]
  • A. G. D. Spradlin chosen
    G. D. Spradlin was an American character actor known for his authoritative roles in films such as "The Godfather Part II" and "Apocalypse Now."
  • B. David Spradley
    David Spradley is an American songwriter and producer best known for his work in R&B and funk music, including contributions to hit songs like "So Many Tears."
  • C. David E. Talbert
    David E. Talbert is an American playwright, author, and filmmaker known for his romantic comedies and stage-to-screen adaptations.
  • D. Glenn S. Dumke
    Glenn S. Dumke was an American historian and academic administrator best known for leading and expanding the California State University system during his long tenure as its chancellor.
  • E. Bruce A. Blakeman
    Bruce A. Blakeman is an American politician and attorney who serves as the County Executive of Nassau County, New York.
  • 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_69d6ada0640c81908c061d7fb3d47786 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d7b6bd08190b30beba393a5b1e7 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6349716fc8190997b54a50d29827a completed May 2, 2026, 5:29 p.m.
Created at: April 8, 2026, 9:55 p.m.