Triple

T15654793
Position Surface form Disambiguated ID Type / Status
Subject A533 E376408 entity
Predicate connects P390 FINISHED
Object Winsford E327236 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: Winsford | Statement: [A533, connects, Winsford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Winsford
Context triple: [A533, connects, Winsford]
  • A. Winsford chosen
    Winsford is a town in Cheshire, England, known historically for its salt mining industry and its location along the River Weaver.
  • B. Knutsford
    Knutsford is a historic market town in Cheshire, England, known for its picturesque streets, affluent character, and literary associations with Elizabeth Gaskell.
  • C. Runcorn
    Runcorn is an industrial town in Cheshire, England, situated on the southern bank of the River Mersey and known for its chemical industry and transport links.
  • D. Willaston
    Willaston is a village on the Wirral Peninsula in England, known for its rural character and proximity to scenic walking and cycling routes.
  • E. Willaston
    Willaston is a village in Cheshire, England, situated near the town of Crewe.
  • 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_69d85cd1564c8190991adda63bfab4b0 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ef089948190902ec22f4d7bc932 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff875e49748190a2a4aceb649762b4 completed May 9, 2026, 7:13 p.m.
Created at: April 10, 2026, 4:15 a.m.