Triple

T23452853
Position Surface form Disambiguated ID Type / Status
Subject River Okement E567831 entity
Predicate region P40 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: [River Okement, region, West Devon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: West Devon
Context triple: [River Okement, region, 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_69e2458b4c888190b1d7998f9862a558 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a694f19081909117bc9b10ca8a83 completed April 29, 2026, 6:35 a.m.
Created at: April 17, 2026, 5:52 p.m.