Triple

T18690743
Position Surface form Disambiguated ID Type / Status
Subject Alexandre Trauner E456990 entity
Predicate workedOn P3 FINISHED
Object Zazie in the Metro NE NERFINISHED

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: Zazie in the Metro | Statement: [Alexandre Trauner, workedOn, Zazie in the Metro]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zazie in the Metro
Context triple: [Alexandre Trauner, workedOn, Zazie in the Metro]
  • A. Zazie in the Metro chosen
    Zazie in the Metro is a 1960 French comedy film, based on Raymond Queneau’s novel, known for its anarchic humor and inventive visual style.
  • B. Zazie
    Zazie is a German-American actress known for her roles in projects like the TV series "Atlanta" and the film "Deadpool 2."
  • C. La Puce à l’oreille
    La Puce à l’oreille is a classic French farce by playwright Georges Feydeau, renowned for its intricate misunderstandings, rapid-fire dialogue, and expertly constructed comic situations.
  • D. Le Ventre de Paris
    Le Ventre de Paris is a naturalist novel by Émile Zola that vividly portrays life around Paris’s central market, Les Halles, while exploring themes of social conflict, hunger, and abundance.
  • E. Sous le ciel de Paris
    Sous le ciel de Paris is a classic French chanson, famously interpreted by Juliette Gréco, that evokes the romantic and poetic atmosphere of Paris.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69e562e28e5c8190b0033c1667d50e05 completed April 19, 2026, 11:18 p.m.
Created at: April 10, 2026, 11:49 a.m.