Triple

T15824841
Position Surface form Disambiguated ID Type / Status
Subject Transavia E383711 entity
Predicate callsign P1565 FINISHED
Object TRANSAVIA E383713 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, callsign, TRANSAVIA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TRANSAVIA
Context triple: [Transavia, callsign, TRANSAVIA]
  • A. TRANSAVIA chosen
    TRANSAVIA is a Dutch low-cost airline operating scheduled and charter flights across Europe and surrounding regions.
  • B. Transbordeur
    Transbordeur is a renowned concert hall and cultural venue in Villeurbanne, France, known for hosting a wide range of contemporary music events and performances.
  • C. TRANSAT
    TRANSAT is the radio callsign used by Air Transat, a Canadian leisure airline operating charter and scheduled flights primarily between Canada and vacation destinations.
  • D. Island Transvoyager
    Island Transvoyager was the former name of AirSWIFT, a Philippine regional airline operating domestic flights to popular island destinations.
  • E. Travel Air 2000
    The Travel Air 2000 is an American three-seat open-cockpit biplane from the 1920s, widely used for sport flying, training, and barnstorming in the early years of civil aviation.
  • 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_69d86da34c888190976e06c4019d415a completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e11e5f46748190acb46cc482501307 completed April 16, 2026, 5:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff999bba548190a39adc2d0e11c605 completed May 9, 2026, 8:31 p.m.
Created at: April 10, 2026, 4:49 a.m.