Triple

T2059893
Position Surface form Disambiguated ID Type / Status
Subject Mosaic E45766 entity
Predicate brand P1500 FINISHED
Object JetBlue E1838 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: JetBlue | Statement: [Mosaic, brand, JetBlue]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: JetBlue
Context triple: [Mosaic, brand, JetBlue]
  • A. JetBlue Airways chosen
    JetBlue Airways is a major American low-cost airline known for its customer-friendly service, free in-flight entertainment, and extensive route network across the United States, Caribbean, and Latin America.
  • B. Spirit Airlines
    Spirit Airlines is an American ultra-low-cost carrier known for its no-frills service model and extensive network of domestic and Latin American routes.
  • C. Ryan Airlines
    Ryan Airlines was an American aircraft manufacturer and airline best known for building Charles Lindbergh’s Spirit of St. Louis monoplane.
  • D. Silver Airways
    Silver Airways is a U.S. regional airline that primarily operates short-haul flights within Florida and the southeastern United States, as well as to nearby Caribbean destinations.
  • E. Virgin America
    Virgin America was a U.S.-based low-cost airline known for its stylish, tech-friendly in-flight experience and West Coast–focused route network.
  • 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_69a8891a19508190a12ef1e192308dcb completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb9cfdac88190b8b7af1bfea6a78e completed March 7, 2026, 5:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae305036d481908120f74426d02ed5 completed March 9, 2026, 2:28 a.m.
Created at: March 4, 2026, 7:40 p.m.