Triple

T13058861
Position Surface form Disambiguated ID Type / Status
Subject New Addington E327648 entity
Predicate near P350 FINISHED
Object Selsdon E501091 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: Selsdon | Statement: [New Addington, near, Selsdon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Selsdon
Context triple: [New Addington, near, Selsdon]
  • A. Beddington
    Beddington is a suburban area in South London known for its historic village core, green spaces, and proximity to Croydon and central London.
  • B. Burgess Hill
    Burgess Hill is a town in southeastern England known as a commuter hub with residential areas and light industry, situated within the county of West Sussex.
  • C. Westerham
    Westerham is a small historic town in Kent, England, known for its picturesque setting and associations with figures such as Winston Churchill.
  • D. Purley chosen
    Purley is a suburban town in South London known for its residential character and location within the London Borough of Croydon.
  • E. Banstead
    Banstead is a suburban town in southeast England known for its village-like high street and green spaces within the county of Surrey.
  • 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_69d8076e64308190904fb5c93517c901 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d980be37208190962e91f1e19df159 completed April 10, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00179824c88190aeef28a08eb1a0c9 completed May 10, 2026, 5:28 a.m.
Created at: April 9, 2026, 8:58 p.m.