Triple

T23003368
Position Surface form Disambiguated ID Type / Status
Subject Coën E572692 entity
Predicate hasVariant P455 FINISHED
Object Coen 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: Coen | Statement: [Coën, hasVariant, Coen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Coen
Context triple: [Coën, hasVariant, Coen]
  • A. Coen chosen
    Coen is a small, remote township in Queensland’s Cape York Peninsula, known as a service and supply hub for travelers and Indigenous communities in the region.
  • B. Coen
    Coen is a Dutch surname most notably associated with Jan Pieterszoon Coen, a 17th-century officer of the Dutch East India Company and colonial governor-general of the Dutch East Indies.
  • C. Coen brothers
    The Coen brothers are an acclaimed American filmmaking duo, Joel and Ethan Coen, known for their darkly comic, genre-bending films such as Fargo, The Big Lebowski, and No Country for Old Men.
  • D. Ethan Coen
    Ethan Coen is an American filmmaker, screenwriter, and producer best known as one half of the Coen brothers duo behind acclaimed films such as Fargo, No Country for Old Men, and The Big Lebowski.
  • E. Chris Coen
    Chris Coen is a film producer best known for his work on the psychological thriller "Funny Games U.S."
  • 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_69e245b6a3ac81908087599eefe3e365 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183549bdc81908fdcd44e2c92f7c4 completed April 29, 2026, 4:04 a.m.
Created at: April 17, 2026, 3:50 p.m.