Triple

T10298053
Position Surface form Disambiguated ID Type / Status
Subject Largs E241548 entity
Predicate near P350 FINISHED
Object Fairlie E763330 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: Fairlie | Statement: [Largs, near, Fairlie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fairlie
Context triple: [Largs, near, Fairlie]
  • A. Fairlie chosen
    Fairlie is a small coastal village in North Ayrshire, Scotland, known for its scenic Firth of Clyde shoreline and views toward the Isle of Arran.
  • B. Fairlie
    Fairlie is a small rural service town in New Zealand’s South Island, known as a gateway to the Mackenzie District and nearby alpine and lake attractions.
  • C. Fairlea
    Fairlea is a small unincorporated community in Greenbrier County, West Virginia, known for hosting the annual West Virginia State Fair.
  • D. Glenlee
    Glenlee is a historic three-masted steel sailing ship, now preserved as a museum ship on the River Clyde in Glasgow, Scotland.
  • E. Kincorth
    Kincorth is a residential area in the south of Aberdeen, Scotland, known for its post-war housing and proximity to the River Dee.
  • 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_69d381aaafc08190af475ef58dc16aba completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d2ed50908190962f0d6d049fb964 completed April 7, 2026, 9:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d71d2cc9c48190bc36f6a4f8144b7f completed April 9, 2026, 3:29 a.m.
Created at: April 6, 2026, 11:43 a.m.