Triple

T11978290
Position Surface form Disambiguated ID Type / Status
Subject LTBJ E285090 entity
Predicate servesAirline P12356 FINISHED
Object SunExpress E285094 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: SunExpress | Statement: [LTBJ, servesAirline, SunExpress]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SunExpress
Context triple: [LTBJ, servesAirline, SunExpress]
  • A. SunExpress chosen
    SunExpress is a Turkish-German leisure airline that primarily operates holiday and charter flights, especially to and from Turkey and popular European destinations.
  • B. Batik Air
    Batik Air is an Indonesian full-service airline operating domestic and regional flights as part of the Lion Air Group.
  • C. Crossair
    Crossair was a former Swiss regional airline that served as the main predecessor to Swiss International Air Lines after the collapse of Swissair.
  • D. Virgin Express
    Virgin Express was a Belgian low-cost airline that operated primarily from Brussels in the 1990s and early 2000s before being merged into Brussels Airlines.
  • E. Sky Airline
    Sky Airline is a Chilean low-cost carrier that operates domestic and regional flights across South America.
  • 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_69d6ab2eaeb881909f7914758f859413 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d90393cfb08190b5b45d3e5e32fad3 completed April 10, 2026, 2:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69f471f6afc48190856a0f7c486b28aa completed May 1, 2026, 9:27 a.m.
Created at: April 8, 2026, 9:46 p.m.