Triple

T21924261
Position Surface form Disambiguated ID Type / Status
Subject Thomson and Sandilands E541400 entity
Predicate location P40 FINISHED
Object Glasgow 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: Glasgow | Statement: [Thomson and Sandilands, location, Glasgow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Glasgow
Context triple: [Thomson and Sandilands, location, Glasgow]
  • A. Glasgow chosen
    Glasgow is Scotland’s largest city, historically a major industrial and shipbuilding center, known for its rich cultural scene, distinctive architecture, and role as a key urban hub in the United Kingdom.
  • B. Glasgo
    Glasgo is a small village located within the town of Griswold in eastern Connecticut, known for its rural character and proximity to Glasgo Pond.
  • C. Glasgwm
    Glasgwm is a mountain in southern Snowdonia, Wales, known for its rugged terrain and scenic views within the Aran range.
  • D. Edinburgh
    Edinburgh is the historic and cultural heart of Scotland, renowned for its medieval Old Town, elegant Georgian New Town, and world-famous arts festivals.
  • E. Dundee
    Dundee is a small village in Yates County, New York, known for its rural character within the Finger Lakes region.
  • 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_69e0c47d74488190a15119108794a307 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1233dc504819083ee27e253805189 completed April 28, 2026, 9:14 p.m.
Created at: April 16, 2026, 7:45 p.m.