Triple

T585293
Position Surface form Disambiguated ID Type / Status
Subject Marseille E15143 entity
Predicate hasTwinTown P919 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: [Marseille, hasTwinTown, Glasgow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Glasgow
Context triple: [Marseille, hasTwinTown, 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. 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.
  • C. Dundee
    Dundee is a coastal city in eastern Scotland known for its historic jute industry, maritime heritage, and contemporary cultural and design scene.
  • D. Glasgow and Edinburgh
    Glasgow and Edinburgh are Scotland’s two largest and most prominent cities, serving as major cultural, economic, and transport hubs in the country.
  • E. Paisley
    Paisley is a large town in the west of Scotland known for its historic textile industry and as the origin of the famous paisley pattern.
  • 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_69a4935783b8819082b77726ec10cc42 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49b9874c88190bd1e08d4689ea124 completed March 1, 2026, 8:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac7623e27c81909022abd9950753d1 completed March 7, 2026, 7:01 p.m.
Created at: March 1, 2026, 7:33 p.m.