Triple

T13656976
Position Surface form Disambiguated ID Type / Status
Subject Fish Tank E326886 entity
Predicate director P255 FINISHED
Object Andrea Arnold E447660 NE FINISHED

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: Andrea Arnold | Statement: [Fish Tank, director, Andrea Arnold]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrea Arnold
Context triple: [Fish Tank, director, Andrea Arnold]
  • A. Andrea Arnold chosen
    Andrea Arnold is an acclaimed British filmmaker known for her gritty, character-driven films such as "Fish Tank" and "American Honey," as well as her work in high-profile television.
  • B. 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."
  • C. Lone Scherfig
    Lone Scherfig is a Danish film director and screenwriter known for her character-driven dramas and romantic comedies, including the acclaimed film "An Education."
  • D. Andrew Haigh
    Andrew Haigh is a British filmmaker known for his nuanced, character-driven work in film and television, including projects like "Weekend," "45 Years," and "Looking."
  • E. Sarah Gavron
    Sarah Gavron is a British film director known for socially conscious dramas such as "Suffragette" and "Brick Lane."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d8076d8270819092afc2f0e9c359a8 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc61d56e4819084ae3c16ecdf4a05 completed April 12, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78b03083c8190855a2a4ee44e4098 completed May 3, 2026, 5:50 p.m.
Created at: April 9, 2026, 9:52 p.m.