Triple

T23379259
Position Surface form Disambiguated ID Type / Status
Subject Cardigan Castle E593693 entity
Predicate locatedInHistoricCounty P1069 FINISHED
Object Cardiganshire 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: Cardiganshire | Statement: [Cardigan Castle, locatedInHistoricCounty, Cardiganshire]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cardiganshire
Context triple: [Cardigan Castle, locatedInHistoricCounty, Cardiganshire]
  • A. Cardiganshire chosen
    Cardiganshire is a historic county in west Wales, centered on the town of Cardigan and known for its rural landscapes and coastal communities along Cardigan Bay.
  • B. Breconshire
    Breconshire is a historic county in south-central Wales, known for its rural landscapes and parts of the Brecon Beacons mountain range.
  • C. Buteshire
    Buteshire is a historic county in western Scotland that encompassed the Isle of Bute and surrounding islands in the Firth of Clyde.
  • D. Somerset
    Somerset is a coastal town in Bristol County, Massachusetts, situated along the Taunton River opposite the city of Fall River.
  • E. Somerset
    Somerset is a city in Pulaski County, Kentucky, known as a regional hub for commerce, healthcare, and recreation near Lake Cumberland.
  • 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_69e25d268a50819095f2fd479da8ef3f completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a3b5e4f0819081a5d4586796677b completed April 29, 2026, 6:22 a.m.
Created at: April 17, 2026, 5:33 p.m.