Triple

T22264296
Position Surface form Disambiguated ID Type / Status
Subject Chatham and Aylesford E550308 entity
Predicate containsTown P847 FINISHED
Object Snodland 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: Snodland | Statement: [Chatham and Aylesford, containsTown, Snodland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Snodland
Context triple: [Chatham and Aylesford, containsTown, Snodland]
  • A. Snodland chosen
    Snodland is a small town in Kent, England, known historically for its cement and paper industries and its location between Maidstone and Rochester.
  • B. Reydon
    Reydon is a village and civil parish in the English county of Suffolk, located near the coastal town of Southwold.
  • C. Thankerton
    Thankerton is a small village in South Lanarkshire, Scotland, situated within the historic district of Clydesdale.
  • D. Wilstead
    Wilstead is a village and civil parish located within the Borough of Bedford in Bedfordshire, England.
  • E. Lowdon
    Lowdon is a surname and given name that serves as a variant spelling of Lowden, used by individuals and families primarily in English-speaking regions.
  • 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_69e11e42adb8819087714772ea606709 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f141ba5c9481909e24067133918ae2 completed April 28, 2026, 11:24 p.m.
Created at: April 16, 2026, 8:39 p.m.