Triple

T15028506
Position Surface form Disambiguated ID Type / Status
Subject Arnhem–Winterswijk railway E378277 entity
Predicate operator P179 FINISHED
Object Arriva E119079 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: Arriva | Statement: [Arnhem–Winterswijk railway, operator, Arriva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arriva
Context triple: [Arnhem–Winterswijk railway, operator, Arriva]
  • A. Arriva chosen
    Arriva is a major European public transport company that operates bus, coach, train, tram, and waterbus services across multiple countries.
  • B. Govia
    Govia is a major British train operating company formed as a joint venture between the Go-Ahead Group and Keolis, running several rail franchises in the United Kingdom.
  • C. Arriva Rail North
    Arriva Rail North was a British train operating company that ran regional and commuter rail services across Northern England under the Northern brand.
  • D. Arriva Poland
    Arriva Poland is a Polish public transport operator providing bus and rail services as part of the wider Arriva Group’s European operations.
  • E. Busbridge
    Busbridge is a small village in Surrey, England, situated near the town of Godalming and known for its rural character and historic church.
  • 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7e0e8c88190ac6f5786b4d4040f completed April 15, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9dd967588190821cf47e9734db21 completed May 9, 2026, 2:37 a.m.
Created at: April 10, 2026, 2:58 a.m.