Triple

T17671883
Position Surface form Disambiguated ID Type / Status
Subject George Airport E440538 entity
Predicate hasAirlineService P12356 FINISHED
Object FlySafair 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: FlySafair | Statement: [George Airport, hasAirlineService, FlySafair]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FlySafair
Context triple: [George Airport, hasAirlineService, FlySafair]
  • A. FlySafair chosen
    FlySafair is a South African low-cost airline known for operating domestic routes with a focus on affordability and reliability.
  • B. AirSial
    AirSial is a Pakistani airline that operates domestic flights, including services to destinations such as Skardu.
  • C. Jetairfly
    Jetairfly was the former brand name of TUI fly Belgium, a Belgian leisure airline operating charter and scheduled flights to holiday destinations across Europe and beyond.
  • D. flydubai
    flydubai is a Dubai-based low-cost airline operating an extensive network of regional and international routes, primarily across the Middle East, Asia, Africa, and Europe.
  • E. SunExpress
    SunExpress is a Turkish-German leisure airline that primarily operates holiday and charter flights, especially to and from Turkey and popular European destinations.
  • 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_69d8b9e87e18819087104a44dc4dc5b1 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e46f69b11c8190b09add33f81776b3 completed April 19, 2026, 6 a.m.
Created at: April 10, 2026, 9:59 a.m.