Triple

T1175729
Position Surface form Disambiguated ID Type / Status
Subject River Witham E25020 entity
Predicate flowsThrough P225 FINISHED
Object Sleaford E77486 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: Sleaford | Statement: [River Witham, flowsThrough, Sleaford]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sleaford
Context triple: [River Witham, flowsThrough, Sleaford]
  • A. Sleaford chosen
    Sleaford is a market town in Lincolnshire, England, known for its historic architecture and role as a local commercial and agricultural center.
  • B. Yorkton
    Yorkton is a small city in southeastern Saskatchewan, Canada, known as a regional hub for agriculture and services.
  • C. Waltham, Lincolnshire
    Waltham, Lincolnshire is a village and civil parish in North East Lincolnshire, England, known for its historic church and rural character near the town of Grimsby.
  • D. Nuneaton
    Nuneaton is a market town in Warwickshire, England, best known as the birthplace of Victorian novelist George Eliot.
  • E. Wisbech
    Wisbech is a historic market town and inland port in the Fens of eastern England, known for its Georgian architecture and agricultural surroundings.
  • 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_69a494267b4c819088c97a59182bf56a completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bd0d5c288190b597dae0fbe3b43b completed March 1, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac6f1a13bc81909da2cfdbad397861 completed March 7, 2026, 6:31 p.m.
Created at: March 1, 2026, 7:45 p.m.