Triple

T14745147
Position Surface form Disambiguated ID Type / Status
Subject William Russ E346447 entity
Predicate notableWork P4 FINISHED
Object Wiseguy E869370 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: Wiseguy | Statement: [William Russ, notableWork, Wiseguy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wiseguy
Context triple: [William Russ, notableWork, Wiseguy]
  • A. Wiseguy chosen
    Wiseguy is an American crime drama television series centered on an undercover agent infiltrating organized crime syndicates.
  • B. Wiseguy
    Wiseguy is a true-crime book by Nicholas Pileggi that chronicles the life of mob associate Henry Hill and the inner workings of the American Mafia.
  • C. Wise Guys
    Wise Guys is a 1986 American mafia comedy film directed by Brian De Palma and produced by Aaron Russo, starring Danny DeVito and Joe Piscopo as low-level mobsters who bungle a job for their boss.
  • D. Gotti
    Gotti is a surname most famously associated with John Gotti, the notorious American mob boss who led New York’s Gambino crime family in the late 20th century.
  • E. Gotti
    Gotti is a 1996 television crime drama film in which Armand Assante portrays notorious mob boss John Gotti.
  • 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_69d822e6f1c88190bc494d491a907114 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7d002708190a32a4a45e96fc389 completed April 14, 2026, 11:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdfb9638648190a2a3eb255ec5ae28 completed May 8, 2026, 3:04 p.m.
Created at: April 10, 2026, 1:30 a.m.