Triple

T19110184
Position Surface form Disambiguated ID Type / Status
Subject Manor Ground E467766 entity
Predicate addressArea P74850 FINISHED
Object Headington 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: Headington | Statement: [Manor Ground, addressArea, Headington]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Headington
Context triple: [Manor Ground, addressArea, Headington]
  • A. Headington chosen
    Headington is a suburban district of Oxford, England, known for its residential character, hospitals, and university campuses.
  • B. Hatton Vale
    Hatton Vale is a rural town in Queensland, Australia, situated in the Lockyer Valley between Brisbane and Toowoomba.
  • C. Highworth
    Highworth is a historic market town in Wiltshire, England, known for its elevated position and traditional architecture.
  • D. Wadhurst
    Wadhurst is a rural village in East Sussex, England, known for its historic High Street, surrounding Wealden countryside, and role as a commuter community for nearby towns and London.
  • E. Hertingfordbury
    Hertingfordbury is a small historic village and civil parish in Hertfordshire, England, known for its rural character and traditional English countryside setting.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e393bafc81908e35a0eba7b807a6 completed April 20, 2026, 8:28 a.m.
Created at: April 10, 2026, 12:04 p.m.