Triple

T267690
Position Surface form Disambiguated ID Type / Status
Subject Eccles E5767 entity
Predicate servedBy P82 FINISHED
Object Northern Trains E9865 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: Northern Trains | Statement: [Eccles, servedBy, Northern Trains]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Northern Trains
Context triple: [Eccles, servedBy, Northern Trains]
  • A. Northern Trains chosen
    Northern Trains is a British train operating company that runs local and regional passenger rail services across Northern England.
  • B. Thameslink
    Thameslink is a major British rail network providing cross-London services that connect destinations across the South East of England.
  • C. TransPennine Express
    TransPennine Express is a British train operating company providing intercity and regional rail services across northern England and into Scotland.
  • D. National Rail
    National Rail is the collective name for the passenger rail services and network in Great Britain, encompassing most regional and intercity train operations outside of urban metro systems.
  • E. Rail Delivery Group
    Rail Delivery Group is the industry body that represents and coordinates Britain’s passenger and freight train operators and Network Rail, working to improve and manage the national rail system.
  • 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_69a2587daeb081909591b9d30f80a271 completed Feb. 28, 2026, 2:52 a.m.
NER Named-entity recognition batch_69a25dacf60c8190a5c3ef455b9a8b20 completed Feb. 28, 2026, 3:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3914d5cd08190bd755e1e65feee2a completed March 1, 2026, 1:07 a.m.
Created at: Feb. 28, 2026, 2:56 a.m.