Triple

T1981014
Position Surface form Disambiguated ID Type / Status
Subject Denzel Washington E43024 entity
Predicate notableWork P4 FINISHED
Object American Gangster E10877 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: American Gangster | Statement: [Denzel Washington, notableWork, American Gangster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: American Gangster
Context triple: [Denzel Washington, notableWork, American Gangster]
  • A. American Gangster chosen
    American Gangster is a 2007 crime drama film starring Denzel Washington and Russell Crowe that chronicles the rise and fall of Harlem drug lord Frank Lucas in 1970s New York City.
  • B. Bugsy
    Bugsy was the notorious American mobster Benjamin Siegel, a key figure in the development of Las Vegas and organized crime in the early 20th century.
  • C. Gangster Squad
    Gangster Squad is a 2013 crime action film set in 1940s–50s Los Angeles, following an elite police unit’s violent battle against mobster Mickey Cohen.
  • D. Sin City
    Sin City is a popular nickname for Las Vegas, Nevada, highlighting its reputation for gambling, nightlife, and adult entertainment.
  • E. Sin City
    Sin City is a 2005 neo-noir crime anthology film, co-directed by Robert Rodriguez and Frank Miller, known for its stylized black-and-white visuals and adaptation of Miller’s graphic novel series.
  • 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_69a88713ddc88190a969715658ebe7a8 completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb81ddddc819099acc2740de0b236 completed March 7, 2026, 5:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae032bc30c8190a136a634580571d9 completed March 8, 2026, 11:15 p.m.
Created at: March 4, 2026, 7:37 p.m.