Triple

T11258198
Position Surface form Disambiguated ID Type / Status
Subject FAOR E266493 entity
Predicate servesAsHubFor P423 FINISHED
Object Mango Airlines E245438 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: Mango Airlines | Statement: [FAOR, servesAsHubFor, Mango Airlines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mango Airlines
Context triple: [FAOR, servesAsHubFor, Mango Airlines]
  • A. Mango Airlines chosen
    Mango Airlines is a South African low-cost airline that operated domestic and regional flights as a budget subsidiary of South African Airways.
  • B. PAL Airlines
    PAL Airlines is a Canadian regional airline that operates passenger and cargo flights primarily throughout Newfoundland and Labrador and other parts of eastern Canada.
  • C. Rex Airlines
    Rex Airlines is an Australian regional airline that operates domestic passenger services across multiple states, connecting major cities with regional and remote communities.
  • D. Coral Sun Airways
    Coral Sun Airways is a regional airline based in Kiribati that operates domestic flights connecting islands such as Tabiteuea.
  • E. Malindo Air
    Malindo Air is a Malaysian hybrid full-service and low-cost airline that became the first operator of the Boeing 737 MAX 8.
  • 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_69d6aac7953c8190b82caf9d7640fdf9 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e935b85c819085e1abf2dd4099c5 completed April 9, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4f410cb508190bb0ceab51075eec5 completed April 19, 2026, 3:26 p.m.
Created at: April 8, 2026, 9:31 p.m.