Triple

T20215541
Position Surface form Disambiguated ID Type / Status
Subject Southern E493611 entity
Predicate parentCompany P254 FINISHED
Object Govia NE NERFINISHED

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: Govia | Statement: [Southern, parentCompany, Govia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Govia
Context triple: [Southern, parentCompany, Govia]
  • A. Govia chosen
    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.
  • B. Abellio
    Abellio is a Dutch-based public transport company that operates train and bus services in the United Kingdom and parts of Europe.
  • C. Keolis
    Keolis is a major French public transport operator that manages and operates bus, tram, metro, and rail networks in numerous cities worldwide.
  • D. Systra
    Systra is a global engineering and consulting firm specializing in mass transit and rail infrastructure projects.
  • E. GVB Ferries
    GVB Ferries is the ferry service operating across Amsterdam’s waterways, providing frequent, short-distance crossings that connect key parts of the city as part of its public transport system.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da6269614c8190bb40475d9d477358 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66ed8cc8c8190889ecadc702010d8 completed April 20, 2026, 6:22 p.m.
Created at: April 11, 2026, 11:38 p.m.