Triple

T18690883
Position Surface form Disambiguated ID Type / Status
Subject Klaus Kinski E456994 entity
Predicate notableRole P22 FINISHED
Object Brian Sweeney Fitzgerald (Fitzcarraldo) NE NERFINISHED

How this triple was built (3 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: Brian Sweeney Fitzgerald (Fitzcarraldo) | Statement: [Klaus Kinski, notableRole, Brian Sweeney Fitzgerald (Fitzcarraldo)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brian Sweeney Fitzgerald (Fitzcarraldo)
Context triple: [Klaus Kinski, notableRole, Brian Sweeney Fitzgerald (Fitzcarraldo)]
  • A. Conrad Riggs
    Conrad Riggs is a television producer best known for his executive production work on major reality TV franchises, including "The Apprentice."
  • B. Conrad Dalton
    Conrad Dalton is a fictional U.S. President on the political drama television series "Madam Secretary."
  • C. Lafe McKee
    Lafe McKee was an American character actor best known for his prolific appearances in early Western films during the silent and early sound eras.
  • D. Quentin Fiore
    Quentin Fiore was an American graphic designer and book designer best known for his innovative, visually experimental collaborations with media theorist Marshall McLuhan in the 1960s.
  • E. Justin Haythe
    Justin Haythe is a British-American screenwriter and novelist known for adapting literary works into acclaimed films such as "Revolutionary Road" and "A Cure for Wellness."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Brian Sweeney Fitzgerald (Fitzcarraldo)
Target entity description: Brian Sweeney Fitzgerald, known as Fitzcarraldo, is the obsessive dreamer and rubber baron protagonist of Werner Herzog’s film "Fitzcarraldo," famed for his quixotic quest to haul a steamship over a mountain to build an opera house in the Amazon.
  • A. Conrad Riggs
    Conrad Riggs is a television producer best known for his executive production work on major reality TV franchises, including "The Apprentice."
  • B. Conrad Dalton
    Conrad Dalton is a fictional U.S. President on the political drama television series "Madam Secretary."
  • C. Lafe McKee
    Lafe McKee was an American character actor best known for his prolific appearances in early Western films during the silent and early sound eras.
  • D. Quentin Fiore
    Quentin Fiore was an American graphic designer and book designer best known for his innovative, visually experimental collaborations with media theorist Marshall McLuhan in the 1960s.
  • E. Justin Haythe
    Justin Haythe is a British-American screenwriter and novelist known for adapting literary works into acclaimed films such as "Revolutionary Road" and "A Cure for Wellness."
  • F. None of above. chosen

Provenance (2 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_69d8d391eb488190ac2e9abf5bf255e4 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e562e3a6d08190b2409bcbf0c42444 completed April 19, 2026, 11:18 p.m.
Created at: April 10, 2026, 11:49 a.m.