Triple

T22611970
Position Surface form Disambiguated ID Type / Status
Subject A557 road E566729 entity
Predicate connects P390 FINISHED
Object Widnes 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: Widnes | Statement: [A557 road, connects, Widnes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Widnes
Context triple: [A557 road, connects, Widnes]
  • A. Widnes chosen
    Widnes is an industrial town in Cheshire, England, historically known for its chemical industry and location on the River Mersey.
  • B. Warrington Rylands
    Warrington Rylands is an English football club based in Warrington, known for its rapid rise through the non-league tiers in recent years.
  • C. Warrington
    Warrington is a large town in Cheshire, England, situated between Liverpool and Manchester on the River Mersey and known historically for its role in industry and transport.
  • D. Wirral
    Wirral is a peninsula in North West England known for its mix of coastal towns, suburban areas, and countryside between the River Mersey and the River Dee.
  • E. 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.
  • 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_69e245884860819081046ce07d5872c4 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f167eb08c88190bf2380fa8575d2da completed April 29, 2026, 2:07 a.m.
Created at: April 17, 2026, 2:57 p.m.