Triple

T663319
Position Surface form Disambiguated ID Type / Status
Subject Fidra E12804 entity
Predicate locatedNear P294 FINISHED
Object North Berwick E28935 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: North Berwick | Statement: [Fidra, locatedNear, North Berwick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: North Berwick
Context triple: [Fidra, locatedNear, North Berwick]
  • A. South Beveland
    South Beveland is a former island and predominantly agricultural region in the province of Zeeland in the southwestern Netherlands, known for its dike systems and polders.
  • B. Wereham
    Wereham is a small rural village in Norfolk, England, known for its historic church and traditional village green.
  • C. Anstruther chosen
    Anstruther is a picturesque fishing village and popular tourist destination on Scotland’s east coast, known for its historic harbour and award-winning fish and chips.
  • D. Wilhelmshaven
    Wilhelmshaven is a coastal city in northwestern Germany known for its major naval base and port on the North Sea.
  • E. Prescot
    Prescot is a historic town in the Metropolitan Borough of Knowsley in Merseyside, England, known for its watchmaking heritage and proximity to Liverpool.
  • 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_69a493355dec819098d4244b2fa34885 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49fd1f0ec819087003d30bbab2fa6 completed March 1, 2026, 8:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5c398cc748190ab720263096064ef completed March 2, 2026, 5:06 p.m.
Created at: March 1, 2026, 7:36 p.m.