Triple

T2636443
Position Surface form Disambiguated ID Type / Status
Subject Durham E59757 entity
Predicate hasLandmark P105 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: [Durham, hasLandmark, Durham Castle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Durham Castle
Context triple: [Durham, hasLandmark, 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. Warkworth Castle
    Warkworth Castle is a medieval fortress in the village of Warkworth in Northumberland, England, noted for its imposing keep and association with the powerful Percy family.
  • 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_69ab4ac8596c8190b34997e73d9e991c completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd8e1fffc81908e4921690098c8db completed March 7, 2026, 7:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69af90b3e9b48190857ae21022a4fb15 completed March 10, 2026, 3:32 a.m.
Created at: March 6, 2026, 9:50 p.m.