Triple

T20722044
Position Surface form Disambiguated ID Type / Status
Subject Harpur Hill E509338 entity
Predicate locatedNear P294 FINISHED
Object Buxton 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: Buxton | Statement: [Harpur Hill, locatedNear, Buxton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Buxton
Context triple: [Harpur Hill, locatedNear, Buxton]
  • A. Buxton
    Buxton is a village in Norfolk, England, known for its rural setting and historic association with the River Bure.
  • B. Buxton chosen
    Buxton is a historic spa town in Derbyshire, England, renowned for its thermal mineral springs and Georgian architecture.
  • C. Buxton
    Buxton is a small city in eastern North Dakota, United States, known for its rural community character and agricultural surroundings.
  • D. Buxton
    Buxton is a village in the Demerara-Mahaica region of Guyana known historically as one of the country’s prominent Afro-Guyanese communities.
  • E. Buxton
    Buxton is an English surname historically associated with several notable figures in British public life, politics, and philanthropy.
  • 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_69e0b4c4cc648190b45fda6e2b20af56 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1d6bdcc8190ba42c44159a2c0d5 completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:27 p.m.