Triple

T11093279
Position Surface form Disambiguated ID Type / Status
Subject Morningside E262308 entity
Predicate adjacentTo P224 FINISHED
Object Merchiston E478025 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: Merchiston | Statement: [Morningside, adjacentTo, Merchiston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Merchiston
Context triple: [Morningside, adjacentTo, Merchiston]
  • A. Lethington
    Lethington is the historic name of Lennoxlove House, a notable Scottish country house with medieval origins and strong ties to prominent Scottish families.
  • B. Dechmont
    Dechmont is a small village in West Lothian, Scotland, known for its rural setting and proximity to Livingston.
  • C. Merchiston Tower chosen
    Merchiston Tower is a historic 16th-century Scottish tower house in Edinburgh, best known as the ancestral home of mathematician and logarithm inventor John Napier.
  • D. Culleredo
    Culleredo is a municipality in the autonomous community of Galicia in northwestern Spain, situated near the city of A Coruña.
  • E. Murieston
    Murieston is a residential suburb of the Scottish new town of Livingston, known for its family housing and green spaces.
  • 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_69d6aa9a40d88190a373e2c7e48285db completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d799ed12d88190a4ad8c346d68f11f completed April 9, 2026, 12:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3e7d3043c8190bdbe0ec51992db0c completed April 18, 2026, 8:21 p.m.
Created at: April 8, 2026, 9:27 p.m.