Triple

T8456937
Position Surface form Disambiguated ID Type / Status
Subject London–Paris E199941 entity
Predicate terminusInUnitedKingdom P78866 FINISHED
Object London St Pancras International railway station E31343 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 St Pancras International railway station | Statement: [London–Paris, terminusInUnitedKingdom, London St Pancras International railway station]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: London St Pancras International railway station
Context triple: [London–Paris, terminusInUnitedKingdom, London St Pancras International railway station]
  • A. London St Pancras International chosen
    London St Pancras International is a major central London railway terminus and international high-speed rail hub, serving Eurostar services to continental Europe as well as domestic routes.
  • B. King’s Cross St Pancras Underground station
    King’s Cross St Pancras Underground station is a major London Tube interchange serving multiple lines beneath the King’s Cross and St Pancras mainline railway terminals.
  • C. London Victoria railway station
    London Victoria railway station is one of London's busiest central railway termini and transport hubs, serving both mainline and Underground services as a key gateway to the south of England and Gatwick Airport.
  • D. London Paddington station
    London Paddington station is a major central London railway terminus and London Underground hub, designed by Isambard Kingdom Brunel, serving intercity, regional, and airport services including links to Heathrow.
  • E. London Waterloo railway station
    London Waterloo railway station is a major central London terminus and one of the busiest railway stations in the United Kingdom, serving as a key hub for suburban and long-distance services in the south of England.
  • 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: terminusInUnitedKingdom
Context triple: [London–Paris, terminusInUnitedKingdom, London St Pancras International railway station]
  • A. terminusB_country chosen
    Indicates that the country specified is the location of the endpoint (terminus B) of a route, connection, or infrastructure segment.
  • B. locatedInBritishCountry
    Indicates that one entity is geographically or administratively situated within a country that is part of the United Kingdom.
  • C. terminusA_country
    Indicates the country in which the starting terminus (terminus A) of a route, line, or connection is located.
  • D. primaryLondonTerminal
    Indicates that a given station serves as the main London terminal for a particular rail service or route.
  • E. secondaryLondonTerminal
    Indicates that a location serves as a secondary terminal in London associated with a primary London terminal for a given service or route.
  • 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_69ca8318231881908fd1bc1c4d45d286 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe48f180c8190a71cf9d7248ade60 completed March 31, 2026, 3:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebb52978481909c60e43abd496746 completed April 2, 2026, 6:54 p.m.
PD Predicate disambiguation batch_69cbd0fc634481909842c0a30077bfde completed March 31, 2026, 1:49 p.m.
Created at: March 30, 2026, 6:10 p.m.