Triple

T7839346
Position Surface form Disambiguated ID Type / Status
Subject Don McCullin E181764 entity
Predicate residence P75 FINISHED
Object Somerset, England E59760 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: Somerset, England | Statement: [Don McCullin, residence, Somerset, England]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Somerset, England
Context triple: [Don McCullin, residence, Somerset, England]
  • A. Somerset chosen
    Somerset is a historic county in South West England known for its rural landscapes, coastal areas, and cities such as Bath and Wells.
  • B. Somerset
    Somerset is a coastal town in Bristol County, Massachusetts, situated along the Taunton River opposite the city of Fall River.
  • C. Somerset
    Somerset is a borough in southwestern Pennsylvania that serves as the county seat of Somerset County and a gateway to the scenic Laurel Highlands region.
  • D. Wells, Somerset
    Wells, Somerset is a historic cathedral city in southwest England, renowned for its medieval architecture and status as one of the smallest cities in the UK.
  • E. Berkshire, England
    Berkshire, England is a historic county in South East England known for its royal connections, including Windsor Castle, and its picturesque Thames-side towns.
  • 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_69ca8284a25c8190a1a20afad30da792 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb14c4680481908628d22bbe4842f4 completed March 31, 2026, 12:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5abff2a88190a2f988b8b041ebb0 completed March 31, 2026, 5:25 a.m.
Created at: March 30, 2026, 4:47 p.m.