Triple

T15732740
Position Surface form Disambiguated ID Type / Status
Subject Worsley interchange area E381383 entity
Predicate near P350 FINISHED
Object Walkden E115758 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: Walkden | Statement: [Worsley interchange area, near, Walkden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Walkden
Context triple: [Worsley interchange area, near, Walkden]
  • A. Walkden chosen
    Walkden is a suburban town in the City of Salford, Greater Manchester, England, with its own railway station on the Atherton line.
  • B. Barnt Green
    Barnt Green is a village in Worcestershire, England, known as a commuter settlement south of Birmingham with good rail links and surrounding countryside.
  • C. Skelton Green
    Skelton Green is a small village in North Yorkshire, England, situated near the North Sea coast and historically associated with the Teesside area.
  • D. Leylands
    Leylands is a residential neighbourhood within the town of Burgess Hill in West Sussex, England.
  • E. Torresdale
    Torresdale is a residential neighborhood in the far northeastern section of Philadelphia, Pennsylvania, known for its proximity to the Delaware River and suburban character.
  • 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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fd3614481908b2694b1d3550058 completed April 16, 2026, 2:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff82fed7888190b45f28ac91e0079e completed May 9, 2026, 6:54 p.m.
Created at: April 10, 2026, 4:46 a.m.