Triple

T2505008
Position Surface form Disambiguated ID Type / Status
Subject Greater Glasgow E52556 entity
Predicate hasSuburb P747 FINISHED
Object Strathaven E281985 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: Strathaven | Statement: [Greater Glasgow, hasSuburb, Strathaven]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Strathaven
Context triple: [Greater Glasgow, hasSuburb, Strathaven]
  • A. Strathaven chosen
    Strathaven is a historic market town in South Lanarkshire, Scotland, known for its rural surroundings, annual hot air balloon festival, and landmark Strathaven Castle.
  • B. Inveresk
    Inveresk is a historic village in East Lothian, Scotland, known for its well-preserved Georgian architecture and scenic setting near the coast.
  • C. Cambuslang
    Cambuslang is a suburban town in Scotland situated near Glasgow, known historically for its coal mining and industrial heritage.
  • D. Lesmahagow
    Lesmahagow is a small town in South Lanarkshire, Scotland, known historically for its abbey and rural surroundings.
  • E. Cardenden
    Cardenden is a village in Fife, Scotland, known primarily as a former mining community with a railway station on the local commuter network.
  • 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_69ab4957b3a88190adf968ae0c1b931c completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd1cec9f48190848b6129aa394ce4 completed March 7, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69b31a46eea081909e1faf639f7789ff completed March 12, 2026, 7:55 p.m.
Created at: March 6, 2026, 9:46 p.m.