Triple

T17904284
Position Surface form Disambiguated ID Type / Status
Subject Andrea Arnold E447660 entity
Predicate notableWork P4 FINISHED
Object Milk 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: Milk | Statement: [Andrea Arnold, notableWork, Milk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Milk
Context triple: [Andrea Arnold, notableWork, Milk]
  • A. Milk chosen
    Milk is a 2008 biographical film about gay rights activist and politician Harvey Milk, directed by Gus Van Sant and starring Sean Penn.
  • B. Milk
    Milk is a nutrient-rich white liquid produced by the mammary glands of mammals and widely consumed as a staple food and beverage by humans.
  • C. Milch
    Milch is a German surname most notably borne by Erhard Milch, a high-ranking Luftwaffe officer during World War II.
  • D. Susu
    The Susu are a West African ethnic group primarily found in Guinea, known for their Mande language, Islamic heritage, and significant role in regional trade and culture.
  • E. Moloko
    Moloko was a British electronic music duo known for their eclectic blend of trip hop, dance, and pop, and for hits like "Sing It Back" and "The Time Is Now."
  • 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_69d8b9f6d394819082a6d69fd1e23d2f completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49e9a9cfc8190879fc36dfdeb562b completed April 19, 2026, 9:21 a.m.
Created at: April 10, 2026, 10:19 a.m.