Triple

T14594522
Position Surface form Disambiguated ID Type / Status
Subject Payday E342523 entity
Predicate director P255 FINISHED
Object Daryl Duke E982383 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: Daryl Duke | Statement: [Payday, director, Daryl Duke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Daryl Duke
Context triple: [Payday, director, Daryl Duke]
  • A. Daryl Duke chosen
    Daryl Duke was a Canadian film and television director best known for his work on acclaimed miniseries and feature films during the 1970s and 1980s.
  • B. Daryl Sattler
    Daryl Sattler is an American professional soccer goalkeeper best known for his standout performances in the North American Soccer League, particularly with the San Antonio Scorpions.
  • C. Tony Darrow
    Tony Darrow is an American actor best known for his supporting roles as mobsters in films and television, particularly in Martin Scorsese’s crime dramas.
  • D. Don Roderick
    Don Roderick is the legendary last Visigothic king of Spain, often depicted in literature as a tragic figure whose downfall heralds the Moorish conquest of the Iberian Peninsula.
  • E. Luke Duke
    Luke Duke is a main character from the television series and film "The Dukes of Hazzard," known as one of the Duke cousins who get into high-speed adventures and trouble in Hazzard County.
  • 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_69d822ddc0f081909cd8163c7de298cd completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb43480d8819084a707e56da2c237 completed April 14, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd94c60448819098cfab7dd292f0cd completed May 8, 2026, 7:46 a.m.
Created at: April 10, 2026, 1:24 a.m.