Triple

T18512160
Position Surface form Disambiguated ID Type / Status
Subject John Paston E452367 entity
Predicate familyName P18 FINISHED
Object Paston 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: Paston | Statement: [John Paston, familyName, Paston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paston
Context triple: [John Paston, familyName, Paston]
  • A. Paston chosen
    Paston is an English surname historically associated with a prominent gentry family from Norfolk, known for the medieval Paston Letters.
  • B. Thrupp
    Thrupp is a small canal-side village in Oxfordshire, England, known for its historic wharf and picturesque setting along the Oxford Canal.
  • C. Pocklington
    Pocklington is a small market town in the East Riding of Yorkshire, England, known for its historic architecture and surrounding Wolds countryside.
  • D. Baverstock
    Baverstock is a small rural hamlet in Wiltshire, England, known for its historic church and tranquil countryside setting.
  • E. Haltwhistle
    Haltwhistle is a small town in Northumberland, England, known as a gateway to Hadrian’s Wall and the surrounding Tyne Valley countryside.
  • 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_69d8d386df84819092355ebb260d848e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e53346f9488190bc2e4570564bede0 completed April 19, 2026, 7:55 p.m.
Created at: April 10, 2026, 11:36 a.m.