Triple

T3750207
Position Surface form Disambiguated ID Type / Status
Subject Transavia E81309 entity
Predicate brandName P1500 FINISHED
Object transavia E81309 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: transavia | Statement: [Transavia, brandName, transavia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: transavia
Context triple: [Transavia, brandName, transavia]
  • A. Transavia chosen
    Transavia is a Dutch low-cost airline operating scheduled and charter flights across Europe and North Africa.
  • B. Transavia France
    Transavia France is a French low-cost airline and subsidiary of the Air France-KLM group, operating primarily short- and medium-haul leisure routes across Europe and the Mediterranean.
  • C. KLM Cityhopper
    KLM Cityhopper is a Dutch regional airline and subsidiary of KLM that operates short-haul flights across Europe, primarily feeding traffic into KLM’s main network.
  • D. Martinair
    Martinair is a Dutch airline based in the Netherlands that operates both cargo and charter passenger services, historically linked to KLM.
  • E. KLM
    KLM is the flag carrier airline of the Netherlands and one of the world's oldest airlines still operating under its original name.
  • 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_69ad8b19b7b08190a6188804e99c53e9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcb6d0ac4819092c9a41cc60f518d completed March 8, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4db31f964819087bab143f638754f completed March 14, 2026, 3:51 a.m.
Created at: March 8, 2026, 3:35 p.m.