Triple

T13890313
Position Surface form Disambiguated ID Type / Status
Subject Govia Thameslink Railway E333952 entity
Predicate servesAirport P6864 FINISHED
Object Gatwick Airport E13320 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: Gatwick Airport | Statement: [Govia Thameslink Railway, servesAirport, Gatwick Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gatwick Airport
Context triple: [Govia Thameslink Railway, servesAirport, Gatwick Airport]
  • A. Gatwick Airport chosen
    Gatwick Airport is a major international airport serving the London area and is one of the busiest airports in the United Kingdom.
  • B. Heathrow Airport
    Heathrow Airport is the United Kingdom’s largest and busiest international airport, serving as a major global aviation hub for London.
  • C. Stansted Airport
    Stansted Airport is a major international airport serving the London area, particularly known as a hub for low-cost and European short-haul flights.
  • D. London International Airport
    London International Airport is a regional airport serving the city of London and surrounding areas in southwestern Ontario, Canada.
  • E. Bristol Airport
    Bristol Airport is a major regional airport in South West England serving domestic and international flights, notably as a key base for low-cost carriers like easyJet.
  • 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_69d81c5dd2d48190b7a5fc1e009de936 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de23a3a24881908d81d634622fbbcc completed April 14, 2026, 11:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69fd192b5e508190b2d385657f9e358f completed May 7, 2026, 10:58 p.m.
Created at: April 9, 2026, 10:15 p.m.