Triple

T3887263
Position Surface form Disambiguated ID Type / Status
Subject BY E92971 entity
Predicate associatedBrand P1500 FINISHED
Object TUI E65777 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: TUI | Statement: [BY, associatedBrand, TUI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TUI
Context triple: [BY, associatedBrand, TUI]
  • A. TUI Airways
    TUI Airways is a British charter and scheduled airline that primarily serves leisure destinations across Europe and worldwide as part of the TUI Group.
  • B. TUI Group (historical) chosen
    TUI Group (historical) was a major European tourism and travel conglomerate that owned and operated various airlines, tour operators, and travel agencies before its later restructuring and rebranding.
  • C. Morris Travel
    Morris Travel was a travel agency business that owned and operated Morris Air before the airline was acquired by Southwest Airlines.
  • D. TUI fly Belgium
    TUI fly Belgium is a Belgian leisure airline that operates charter and scheduled flights to holiday destinations across Europe, Africa, and the Middle East.
  • E. TAP Group
    TAP Group is the holding company that owns and oversees TAP Air Portugal and its related aviation and travel businesses.
  • 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_69b533788a70819089d028cee84a7e87 completed March 14, 2026, 10:07 a.m.
Created at: March 9, 2026, 3:20 p.m.