Triple

T20700023
Position Surface form Disambiguated ID Type / Status
Subject Blackrod E508753 entity
Predicate nearbySettlement P350 FINISHED
Object Adlington 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: Adlington | Statement: [Blackrod, nearbySettlement, Adlington]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adlington
Context triple: [Blackrod, nearbySettlement, Adlington]
  • A. Adlington chosen
    Adlington is a small town in Lancashire, England, situated near Horwich and known historically for its role in the region’s textile and coal industries.
  • B. Didlington
    Didlington is a small village in Norfolk, England, known for its rural landscape, historic estate, and proximity to the River Wissey.
  • C. Leylands
    Leylands is a residential neighbourhood within the town of Burgess Hill in West Sussex, England.
  • D. Walkden
    Walkden is a suburban town in the City of Salford, Greater Manchester, England, with its own railway station on the Atherton line.
  • E. Colne
    Colne is a historic market town in Lancashire, England, known for its textile heritage and location near the Pennine hills.
  • 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_69e0b4c2b2a481909e31e9cb8f81ab55 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c18a77308190b7c2517d82a145cd completed April 21, 2026, 12:15 a.m.
Created at: April 16, 2026, 12:12 p.m.