Triple

T11874641
Position Surface form Disambiguated ID Type / Status
Subject William Cullen E282493 entity
Predicate residence P75 FINISHED
Object Glasgow E7418 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: Glasgow | Statement: [William Cullen, residence, Glasgow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Glasgow
Context triple: [William Cullen, residence, 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. Glasgwm
    Glasgwm is a mountain in southern Snowdonia, Wales, known for its rugged terrain and scenic views within the Aran range.
  • C. 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.
  • D. Dundee
    Dundee is a small village in Yates County, New York, known for its rural character within the Finger Lakes region.
  • E. Dundee
    Dundee is a coastal city in eastern Scotland known for its historic jute industry, maritime heritage, and contemporary cultural and design scene.
  • 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_69d6ab2945d081908a5851c916cbcfb5 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8be1a22448190bd0722188c14d7bd completed April 10, 2026, 9:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69f417302ffc81908d222c4e01fa3e95 completed May 1, 2026, 3 a.m.
Created at: April 8, 2026, 9:44 p.m.