Triple

T21187514
Position Surface form Disambiguated ID Type / Status
Subject Torksey Castle E522120 entity
Predicate locatedIn P40 FINISHED
Object Torksey 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: Torksey | Statement: [Torksey Castle, locatedIn, Torksey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Torksey
Context triple: [Torksey Castle, locatedIn, Torksey]
  • A. Torksey chosen
    Torksey is a small historic village in Lincolnshire, England, known for its location on the River Trent and its medieval and Viking-era heritage.
  • B. Uttoxeter
    Uttoxeter is a historic market town in central England known for its racecourse and rural Staffordshire setting.
  • C. Tuxford
    Tuxford is a small historic market town in Nottinghamshire, England, known for its traditional architecture and rural surroundings.
  • D. Caddington
    Caddington is a village and civil parish in Bedfordshire, England, situated near the town of Dunstable.
  • E. Kintbury
    Kintbury is a rural village in Berkshire, England, known for its picturesque countryside setting and historic charm.
  • 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_69e0b50ef1d48190b063aa342667df22 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7302222788190aa55ee0ed7342498 completed April 21, 2026, 8:06 a.m.
Created at: April 16, 2026, 3:07 p.m.