Triple

T598707
Position Surface form Disambiguated ID Type / Status
Subject Lord North E11444 entity
Predicate memberOfParliamentFor P14627 FINISHED
Object Banbury E38824 NE FINISHED

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: Banbury | Statement: [Lord North, memberOfParliamentFor, Banbury]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Banbury
Context triple: [Lord North, memberOfParliamentFor, Banbury]
  • A. Banbury chosen
    Banbury is a historic market town in Oxfordshire, England, known for its medieval cross, canal-side setting, and association with the traditional Banbury cake.
  • B. Bicester
    Bicester is a historic market town in Oxfordshire, England, best known today for its rapid growth and the popular designer outlet shopping destination Bicester Village.
  • C. Didcot
    Didcot is a town in Oxfordshire, England, known historically for its railway junction and nearby power stations.
  • D. Wantage
    Wantage is a historic market town in Oxfordshire, England, best known as the birthplace of King Alfred the Great.
  • E. Chippenham
    Chippenham is a historic market town in Wiltshire, England, known for its location on the River Avon and its role as a regional commercial and commuter hub.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a4932779b881908688590d59c71900 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49d776c6c819081b41a9b55041cd5 completed March 1, 2026, 8:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69a64a48e53081908e5d5e093edb5e75 completed March 3, 2026, 2:41 a.m.
Created at: March 1, 2026, 7:35 p.m.