Triple

T1814026
Position Surface form Disambiguated ID Type / Status
Subject County Durham E40394 entity
Predicate knownFor P22 FINISHED
Object Durham Castle E61340 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: Durham Castle | Statement: [County Durham, knownFor, Durham Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Durham Castle
Context triple: [County Durham, knownFor, Durham Castle]
  • A. Durham Castle chosen
    Durham Castle is a Norman fortress in Durham, England, that now forms part of Durham University and serves as a college and historic landmark.
  • B. Newcastle Castle
    Newcastle Castle is a medieval fortress in Newcastle upon Tyne, England, that gave the city its name and stands as one of its most significant historic monuments.
  • C. Scarborough Castle
    Scarborough Castle is a medieval fortress and coastal ruin overlooking the North Sea in the town of Scarborough, England.
  • D. Canterbury Castle
    Canterbury Castle is a Norman-era stone fortress in Canterbury, Kent, now a historic ruin and one of England’s oldest surviving castles.
  • E. Barnard Castle
    Barnard Castle is a historic market town in northern England, best known for its medieval castle ruins overlooking the River Tees.
  • 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_69a88643a3388190a612f2ebe1fb29e7 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa65c905ec8190bea7cd72d218487a completed March 6, 2026, 5:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69adc9aa4c5881908b21829dda45da5a completed March 8, 2026, 7:10 p.m.
Created at: March 4, 2026, 7:32 p.m.