Triple

T8637621
Position Surface form Disambiguated ID Type / Status
Subject Consett E204561 entity
Predicate postTown P2711 FINISHED
Object CONSETT E204561 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: CONSETT | Statement: [Consett, postTown, CONSETT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CONSETT
Context triple: [Consett, postTown, CONSETT]
  • A. Consett chosen
    Consett is a town in north-west County Durham, England, historically known for its steelworks and industrial heritage.
  • B. Nacton
    Nacton is a village and civil parish in Suffolk, England, situated near the River Orwell and known for its rural character and historic estates.
  • C. Blyth
    Blyth is a coastal town and port in southeast Northumberland, England, known historically for coal mining and shipbuilding.
  • D. Morpeth
    Morpeth is a historic market town in Northumberland, England, known for its traditional architecture and role as a local commercial and administrative centre.
  • E. Lynton
    Lynton is a small coastal town in North Devon, England, known for its dramatic cliffside setting above Lynmouth and its Victorian-era cliff railway.
  • 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_69ca834b903c8190add96cc651e1a477 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc476255508190b3e5855232b399a0 completed March 31, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebc2c2b84819087a9f23b47c607e8 completed April 2, 2026, 6:57 p.m.
Created at: March 30, 2026, 6:28 p.m.