Triple

T3881429
Position Surface form Disambiguated ID Type / Status
Subject Norham Castle, Sunrise E92830 entity
Predicate placeOfDepiction P24427 FINISHED
Object Norham E103628 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: Norham | Statement: [Norham Castle, Sunrise, placeOfDepiction, Norham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norham
Context triple: [Norham Castle, Sunrise, placeOfDepiction, Norham]
  • A. Norham chosen
    Norham is a historic village in Northumberland, England, known for its medieval castle overlooking the River Tweed near the Scottish border.
  • B. Framlingham
    Framlingham is a historic market town in Suffolk, England, best known for its well-preserved medieval castle.
  • C. Bamburgh
    Bamburgh is a historic coastal village in Northumberland, England, best known for its imposing medieval castle overlooking the North Sea.
  • D. Hawkenbury
    Hawkenbury is a residential suburb and community area of Royal Tunbridge Wells in Kent, England.
  • E. Hexham
    Hexham is a historic market town in Northumberland, England, known for its medieval abbey and proximity to Hadrian’s Wall.
  • 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_69aed9697de0819087c2559295ff3d12 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeec8d5c1c8190906294177f3ad49e completed March 9, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b51c8983b88190a716987f44487d56 completed March 14, 2026, 8:30 a.m.
Created at: March 9, 2026, 3:20 p.m.