Triple

T23153027
Position Surface form Disambiguated ID Type / Status
Subject Freeheld E578368 entity
Predicate producer P490 FINISHED
Object Celine Rattray 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: Celine Rattray | Statement: [Freeheld, producer, Celine Rattray]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Celine Rattray
Context triple: [Freeheld, producer, Celine Rattray]
  • A. Celine Rattray chosen
    Celine Rattray is a British film producer known for her work on acclaimed independent films and as a co-founder of Maven Pictures.
  • B. Céline Ronté
    Céline Ronté is a French voice actress known for her work dubbing animated films and television series, including roles in the 2018 adaptation of White Fang.
  • C. Céline Lomez
    Céline Lomez is a Canadian actress and singer known for her work in 1970s and 1980s film and television.
  • D. Corinne Cléry
    Corinne Cléry is a French actress best known internationally for her role as O in the 1975 erotic drama film "Story of O" and for appearing as a Bond girl in "Moonraker."
  • E. Céline Granjou
    Céline Granjou is a French sociologist known for her work on environmental issues, scientific practices, and the sociology of innovation.
  • 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_69e245fb8de081908f0eba7b5fd75bc4 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18efaa1fc81908fb1987dbf732f46 completed April 29, 2026, 4:54 a.m.
Created at: April 17, 2026, 4:01 p.m.