Triple

T21991850
Position Surface form Disambiguated ID Type / Status
Subject One Day E543108 entity
Predicate director P255 FINISHED
Object Lone Scherfig 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: Lone Scherfig | Statement: [One Day, director, Lone Scherfig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lone Scherfig
Context triple: [One Day, director, Lone Scherfig]
  • A. Lone Scherfig chosen
    Lone Scherfig is a Danish film director and screenwriter known for her character-driven dramas and romantic comedies, including the acclaimed film "An Education."
  • B. Susanne Bier
    Susanne Bier is an acclaimed Danish film director known for her emotionally intense dramas and the Academy Award-winning film "In a Better World."
  • C. Joanna Hogg
    Joanna Hogg is a British filmmaker known for her introspective, semi-autobiographical dramas such as "The Souvenir" and "The Souvenir Part II."
  • D. Maren Ade
    Maren Ade is a German film director, screenwriter, and producer best known internationally for her critically acclaimed feature "Toni Erdmann."
  • E. Lynne Ramsay
    Lynne Ramsay is a Scottish filmmaker acclaimed for her visually striking, psychologically intense films such as "Ratcatcher," "We Need to Talk About Kevin," and "You Were Never Really Here."
  • 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_69e0c48136b081908831fa907cc02e18 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1270e951081908deda039b47ca84b completed April 28, 2026, 9:30 p.m.
Created at: April 16, 2026, 8:05 p.m.