Triple

T4208571
Position Surface form Disambiguated ID Type / Status
Subject Air France Flight 447 E93840 entity
Predicate aircraftType P1524 FINISHED
Object Airbus A330-203 E38704 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: Airbus A330-203 | Statement: [Air France Flight 447, aircraftType, Airbus A330-203]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Airbus A330-203
Context triple: [Air France Flight 447, aircraftType, Airbus A330-203]
  • A. Airbus A330 chosen
    The Airbus A330 is a wide-body, twin-engine jet airliner designed for medium- to long-haul routes and widely used by airlines around the world.
  • B. Airbus A320-200
    The Airbus A320-200 is a widely used narrow-body, twin-engine jet airliner designed for short- to medium-haul routes and operated by numerous airlines worldwide.
  • C. Airbus A321
    The Airbus A321 is a stretched, single-aisle commercial jet airliner widely used for short- to medium-haul passenger flights.
  • D. Airbus A340
    The Airbus A340 is a long-range, four-engine wide-body commercial airliner designed for intercontinental passenger flights.
  • E. Airbus A310
    The Airbus A310 is a twin-engine, wide-body jet airliner introduced in the early 1980s as a shorter, more efficient derivative of the Airbus A300 for medium- to long-haul routes.
  • 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_69b3451743608190808f41d17ccf2650 completed March 12, 2026, 10:58 p.m.
NER Named-entity recognition batch_69b3480f80208190b08ca6ccfe9c41f6 completed March 12, 2026, 11:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69be4379623c8190856b03238e3ef0dd completed March 21, 2026, 7:06 a.m.
Created at: March 12, 2026, 11:03 p.m.