Triple

T21791538
Position Surface form Disambiguated ID Type / Status
Subject Drewsteignton E537982 entity
Predicate district P2709 FINISHED
Object West Devon 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: West Devon | Statement: [Drewsteignton, district, West Devon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: West Devon
Context triple: [Drewsteignton, district, West Devon]
  • A. West Devon chosen
    West Devon is a largely rural local government district and borough in the county of Devon, England, known for its moorland landscapes and historic market towns.
  • B. North Devon
    North Devon is a largely rural district and coastal area in the county of Devon, England, known for its market towns, beaches, and scenic countryside.
  • C. South West Devon
    South West Devon is a UK parliamentary constituency in Devon, England, represented in the House of Commons.
  • D. Devon
    Devon is a suburban community on the Philadelphia Main Line in Pennsylvania, best known for hosting the historic Devon Horse Show and Country Fair.
  • E. Devon
    Devon is a unisex given name of English origin, often associated with both people and places, including the English county of Devon.
  • 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_69e0c47198f881908cb0d237266c10e9 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0621f95cc8190a3e8619fbf29555a completed April 28, 2026, 7:30 a.m.
Created at: April 16, 2026, 6:52 p.m.