Triple

T5313093
Position Surface form Disambiguated ID Type / Status
Subject Arriva E119079 entity
Predicate hasSubsidiary P254 FINISHED
Object Arriva Portugal 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 Portugal | Statement: [Arriva, hasSubsidiary, Arriva Portugal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arriva Portugal
Context triple: [Arriva, hasSubsidiary, Arriva Portugal]
  • A. Arriva chosen
    Arriva is a major European public transport company that operates bus, coach, train, tram, and waterbus services across multiple countries.
  • B. Irish Ferries
    Irish Ferries is a major Irish ferry company operating passenger and freight services across the Irish Sea and to continental Europe.
  • C. Rede Expressos
    Rede Expressos is a major Portuguese long-distance coach company that operates an extensive intercity and regional bus network across Portugal.
  • D. Lisbon Tramway
    The Lisbon Tramway is a historic network of yellow streetcars that navigate Lisbon’s steep, narrow streets and serve as both public transport and a popular tourist attraction.
  • E. Algarve line
    The Algarve line is a major railway route in southern Portugal that connects the region’s coastal towns and cities along the Algarve.
  • 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_69bd446b57bc8190a513d2e6c40314f3 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd8536c06c81908ef8ba8c39b4fa30 completed March 20, 2026, 5:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf1106ef9c8190811f7b70e784c962 completed March 21, 2026, 9:43 p.m.
Created at: March 20, 2026, 1:54 p.m.