Triple

T15001596
Position Surface form Disambiguated ID Type / Status
Subject Govan E374103 entity
Predicate localGovernmentWard P61409 FINISHED
Object Govan ward E60687 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: Govan ward | Statement: [Govan, localGovernmentWard, Govan ward]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Govan ward
Context triple: [Govan, localGovernmentWard, Govan ward]
  • A. Stockwell ward
    Stockwell ward is a local electoral division within the London Borough of Lambeth, responsible for electing councillors to the borough council.
  • B. Govan chosen
    Govan is a historic district on the River Clyde in Glasgow, Scotland, traditionally known for its shipbuilding industry and working-class roots.
  • C. Townhill ward
    Townhill ward is an electoral division and residential area within the city and county of Swansea in South Wales.
  • D. Ruchill
    Ruchill is a residential district in the north of Glasgow, Scotland, known for its historic park and former hospital site.
  • E. Aston ward
    Aston ward is an electoral division within the Birmingham Ladywood constituency in Birmingham, England.
  • 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_69d85ccc84388190aa151e5173370c8d completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded72fec948190b1c9705538c57976 completed April 15, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe969e2d888190afbb9c8fd8a707c8 completed May 9, 2026, 2:06 a.m.
Created at: April 10, 2026, 2:54 a.m.