Triple

T22997275
Position Surface form Disambiguated ID Type / Status
Subject Talisker E572534 entity
Predicate administrativeArea P8215 FINISHED
Object Highland 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: Highland | Statement: [Talisker, administrativeArea, Highland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Highland
Context triple: [Talisker, administrativeArea, Highland]
  • A. Highland chosen
    Highland is a vast council area in the Scottish Highlands known for its rugged landscapes, remote communities, and iconic natural scenery including mountains, lochs, and coastline.
  • B. Highland
    Highland is the historic Virginia estate of U.S. President James Monroe, now a museum and heritage site open to the public.
  • C. Highland
    Highland is the historic Virginia plantation estate that served as the home of U.S. President James Monroe.
  • D. Highland
    Highland is a commuter rail station on the Needham Line serving passengers in the Boston, Massachusetts area.
  • E. Highland
    Highland is a city in Utah County, Utah, known as a suburban residential community in the Provo–Orem metropolitan area.
  • 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_69e245b6a3ac81908087599eefe3e365 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f182f452b48190951fc5dde56c1bb2 completed April 29, 2026, 4:03 a.m.
Created at: April 17, 2026, 3:50 p.m.