Triple

T12164043
Position Surface form Disambiguated ID Type / Status
Subject Travelcard Zone 5 E289783 entity
Predicate appliesToService P1129 FINISHED
Object London Underground E9036 NE FINISHED

How this triple was built (3 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: London Underground | Statement: [Travelcard Zone 5, appliesToService, London Underground]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: London Underground
Context triple: [Travelcard Zone 5, appliesToService, London Underground]
  • A. London Underground chosen
    The London Underground is a rapid transit system serving Greater London and surrounding areas, famous as one of the world's oldest and most extensive metro networks.
  • B. London Overground
    London Overground is a suburban rail network in London that connects outer districts and some central hubs using a mix of newly built and former National Rail lines, integrated into the city’s public transport system.
  • C. District Railway
    The District Railway was a historic London underground railway company that developed much of what is now the District line, helping to form the core of the city's early subterranean transport network.
  • D. London Underground Metropolitan line
    The London Underground Metropolitan line is one of the network’s oldest and longest lines, running from central London into the north-west suburbs and beyond into Buckinghamshire.
  • E. London Passenger Transport Board
    The London Passenger Transport Board was the public body that managed and coordinated most of the capital’s bus, tram, trolleybus, and underground rail services in London from the 1930s until the late 1940s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: appliesToService
Context triple: [Travelcard Zone 5, appliesToService, London Underground]
  • A. appliesToServiceType
    Indicates that something is relevant or applicable specifically to a particular type or category of service.
  • B. appliesTo chosen
    Indicates that something is relevant, valid, or has effect in relation to a particular entity, case, or context.
  • C. appliesToFeature
    Indicates that something (such as a rule, constraint, or configuration) is relevant to, or governs, a specific feature.
  • D. appliesToPolicy
    Indicates that something is relevant or applicable to a particular policy.
  • E. appliesToConfiguration
    Indicates that something (such as a rule, setting, or operation) is relevant to, affects, or is intended for a particular configuration.
  • F. None of above.

Provenance (4 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_69d6ab4d6c00819095a9a7c35de83cfb completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915d7109481908bf5fe512bba3c89 completed April 10, 2026, 3:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63edddad48190b5b4da184fde27dd completed May 2, 2026, 6:13 p.m.
PD Predicate disambiguation batch_69d9150c18148190bf8152189c0e5fca completed April 10, 2026, 3:19 p.m.
Created at: April 8, 2026, 9:50 p.m.