Triple

T21799763
Position Surface form Disambiguated ID Type / Status
Subject Banff and Buchan E538205 entity
Predicate contains P35 FINISHED
Object Sandhaven 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: Sandhaven | Statement: [Banff and Buchan, contains, Sandhaven]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sandhaven
Context triple: [Banff and Buchan, contains, Sandhaven]
  • A. Sandhaven chosen
    Sandhaven is a small coastal village in the Buchan area of Aberdeenshire, northeast Scotland, historically associated with fishing and maritime activity.
  • B. Stonehaven
    Stonehaven is a coastal town in Aberdeenshire, Scotland, known for its picturesque harbor, historic Dunnottar Castle nearby, and role as a gateway between the Highlands and Lowlands.
  • C. Peacehaven
    Peacehaven is a coastal town on the English Channel in East Sussex, England, known for its cliff-top location and residential character.
  • D. Folehaven
    Folehaven is a residential neighborhood in the Valby district of Copenhagen, Denmark.
  • E. Beachmere
    Beachmere is a coastal suburb in Queensland, Australia, known for its quiet seaside lifestyle along the shores of Moreton Bay.
  • 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_69e0c4733f4081909a86622e7e6d15d2 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f077fede848190b8fe07941d6573d9 completed April 28, 2026, 9:03 a.m.
Created at: April 16, 2026, 6:53 p.m.