Triple

T3887332
Position Surface form Disambiguated ID Type / Status
Subject Thomsonfly E92973 entity
Predicate successor P78 FINISHED
Object Thomson Airways E396976 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: Thomson Airways | Statement: [Thomsonfly, successor, Thomson Airways]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomson Airways
Context triple: [Thomsonfly, successor, Thomson Airways]
  • A. Thomson Airways chosen
    Thomson Airways was a major UK-based charter and scheduled leisure airline that operated holiday flights to destinations worldwide before rebranding as TUI Airways.
  • B. Capital Airlines
    Capital Airlines is a Chinese domestic carrier based in Beijing that operates passenger flights to various destinations across China and select international routes.
  • C. Union Airways
    Union Airways was an early South African airline that later became part of the national carrier, South African Airways.
  • D. Eastern Airways
    Eastern Airways is a British regional airline operating scheduled passenger services across the United Kingdom and parts of Europe.
  • E. Kel Air
    Kel Air is a Tuareg confederation inhabiting the Aïr Mountains region of northern Niger, known for its nomadic pastoralist traditions and historical role in Saharan trade.
  • 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_69aed9697de0819087c2559295ff3d12 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeecabe3548190a5cbf9d0af0bcfb6 completed March 9, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69b52848b5688190aa49774dcd037097 completed March 14, 2026, 9:20 a.m.
Created at: March 9, 2026, 3:20 p.m.