Triple

T19833906
Position Surface form Disambiguated ID Type / Status
Subject Roker E476533 entity
Predicate locatedIn P40 FINISHED
Object Sunderland 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: Sunderland | Statement: [Roker, locatedIn, Sunderland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sunderland
Context triple: [Roker, locatedIn, Sunderland]
  • A. Sunderland chosen
    Sunderland is a coastal city in Tyne and Wear, North East England, historically known for its shipbuilding and coal-mining industries and now a center for services, education, and automotive manufacturing.
  • B. Sunderland
    Sunderland is a small rural community in the township of Brock in Durham Region, Ontario, Canada.
  • C. Sunderland A.F.C.
    Sunderland A.F.C. is a professional football club from Sunderland in North East England, historically successful and known for its passionate fanbase and intense local derbies.
  • D. Newcastle
    Newcastle is a settlement within the Parish of St. Andrew, likely a small town or village in a predominantly rural Caribbean island parish.
  • E. Newcastle
    Newcastle is a seaside resort town in County Down, Northern Ireland, known for its beach and as a gateway to the Mourne Mountains.
  • 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_69d8e51c7c188190b926f3a2a7b5f881 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e656d0347c8190b586c7fe01b61e97 completed April 20, 2026, 4:39 p.m.
Created at: April 10, 2026, 1:50 p.m.