Triple

T9562679
Position Surface form Disambiguated ID Type / Status
Subject Mitsubishi CRJ700 E230711 entity
Predicate hasVariant P455 FINISHED
Object CRJ701 E22404 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: CRJ701 | Statement: [Mitsubishi CRJ700, hasVariant, CRJ701]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CRJ701
Context triple: [Mitsubishi CRJ700, hasVariant, CRJ701]
  • A. Mitsubishi CRJ700
    The Mitsubishi CRJ700 is a regional jet airliner designed for short- to medium-haul routes, commonly used by regional carriers around the world.
  • B. C-7
    C-7 is a commuter rail line in the Cercanías Madrid network that connects central Madrid with various suburban areas.
  • C. Bombardier CRJ family chosen
    The Bombardier CRJ family is a series of regional jet airliners widely used by airlines around the world for short- to medium-haul routes.
  • D. CEDAR JET
    CEDAR JET is the radio callsign used by Middle East Airlines for its commercial flight operations.
  • E. Cargojet
    Cargojet is a Canadian cargo airline specializing in time-sensitive overnight air freight services across North America and select international 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_69ca847e53a88190a60eed7e02257f10 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9965e7b881909df98e933db38092 completed April 1, 2026, 10:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69d152a014a48190925d52967e1fbffe completed April 4, 2026, 6:04 p.m.
Created at: March 30, 2026, 8:03 p.m.