Triple

T21144474
Position Surface form Disambiguated ID Type / Status
Subject Ebor E521015 entity
Predicate hasNearbyTown P3883 FINISHED
Object Armidale 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: Armidale | Statement: [Ebor, hasNearbyTown, Armidale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Armidale
Context triple: [Ebor, hasNearbyTown, Armidale]
  • A. Armidale chosen
    Armidale is a regional city in New South Wales, Australia, known for its university, cool climate, and location on the Northern Tablelands.
  • B. Glen Innes
    Glen Innes is a prominent rural service and commercial centre in the Northern Tablelands region of New South Wales, Australia, known for its Celtic heritage and cool highland climate.
  • C. Glen Innes
    Glen Innes is a suburb in Auckland, New Zealand, known for its residential character and rail connectivity to the city centre.
  • D. Kempsey
    Kempsey is a town in New South Wales, Australia, situated on the Macleay River and serving as a regional centre on the state’s Mid North Coast.
  • E. Kempsey
    Kempsey is a village and civil parish in Worcestershire, England, situated just south of Worcester near the River Severn.
  • 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_69e0b50c6a848190a4e525a77a319b8a completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e723fbb29881909c4036eab46ed440 completed April 21, 2026, 7:15 a.m.
Created at: April 16, 2026, 2:57 p.m.