Triple

T20153841
Position Surface form Disambiguated ID Type / Status
Subject Orry-Kelly E491502 entity
Predicate givenName P17 FINISHED
Object Orry 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: Orry | Statement: [Orry-Kelly, givenName, Orry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orry
Context triple: [Orry-Kelly, givenName, Orry]
  • A. Orry chosen
    Orry is the given name of Orry-Kelly, the acclaimed Australian costume designer who won multiple Academy Awards for his work in Hollywood cinema.
  • B. Parilly
    Parilly is a metro station in the Lyon public transport network, located on line D and serving the southeastern suburbs of the city.
  • C. Arlay
    Arlay is a historic locality in eastern France that served as the principal seat of the noble House of Chalon-Arlay.
  • D. Crozet
    Crozet is a small French commune in the Ain department of eastern France, near the Swiss border and the city of Geneva.
  • E. Noisseville
    Noisseville is a commune in northeastern France, near Metz in the Moselle department, known historically as the site of a major Franco-Prussian War battle.
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667de9bec8190836887c86dbcf28d completed April 20, 2026, 5:52 p.m.
Created at: April 11, 2026, 11:34 p.m.