Triple

T18367556
Position Surface form Disambiguated ID Type / Status
Subject Church Enstone E440087 entity
Predicate constituencyWestminster P2710 FINISHED
Object Witney 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: Witney | Statement: [Church Enstone, constituencyWestminster, Witney]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Witney
Context triple: [Church Enstone, constituencyWestminster, Witney]
  • A. Witney
    Witney is a historic market town in Oxfordshire, England, known for its traditional blanket-making industry and position on the River Windrush.
  • B. Witney chosen
    Witney is a UK parliamentary constituency in Oxfordshire, historically represented by prominent Conservative politicians including former Prime Minister David Cameron.
  • C. Whitney
    "Whitney" is an American sitcom starring comedian Whitney Cummings that aired on NBC in the early 2010s.
  • D. Whitney
    Whitney is a common English surname most famously associated with Eli Whitney, the American inventor of the cotton gin.
  • E. Whitney
    Whitney is the middle name of George Whitney Calhoun, a co-founder of the Green Bay Packers.
  • 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_69d8b918221c8190a9f7b563d64ac677 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e5174f5f448190a1fc67d3039aadd9 completed April 19, 2026, 5:56 p.m.
Created at: April 10, 2026, 10:38 a.m.