Triple

T18241244
Position Surface form Disambiguated ID Type / Status
Subject Las Mercedes Airport E436815 entity
Predicate previouslyServedAirline P12356 FINISHED
Object Avianca NE NERFINISHED

How this triple was built (3 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: Avianca | Statement: [Las Mercedes Airport, previouslyServedAirline, Avianca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Avianca
Context triple: [Las Mercedes Airport, previouslyServedAirline, Avianca]
  • A. Avianca chosen
    Avianca is Colombia’s flagship airline and one of Latin America’s largest carriers, operating an extensive domestic and international route network.
  • B. Caribbean Airlines
    Caribbean Airlines is the state-owned flag carrier of Trinidad and Tobago, operating regional and international flights throughout the Caribbean and to North and South America.
  • C. Copa Airlines
    Copa Airlines is the flag carrier of Panama and a major Latin American airline known for its extensive route network centered on its hub in Panama City.
  • D. AeroCaribbean
    AeroCaribbean was a Cuban regional airline that operated domestic and Caribbean routes, primarily serving as a subsidiary of Cubana de Aviación.
  • E. LATAM Airlines Group
    LATAM Airlines Group is a major Latin American airline holding company formed by the merger of LAN Airlines and TAM Airlines, operating an extensive network of domestic and international routes across the Americas and beyond.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: previouslyServedAirline
Context triple: [Las Mercedes Airport, previouslyServedAirline, Avianca]
  • A. servesAirline chosen
    Indicates that a transportation facility or location provides service for, or is regularly used by, a specified airline.
  • B. associatedAirlineIATA
    Indicates the IATA airline code that is linked or related to a given entity (such as a flight, route, or airport record).
  • C. associatedAirlineFullName
    Indicates the full official name of the airline that is associated with a given entity or record.
  • D. associatedAirlineServiceType
    Indicates the specific type or category of airline service that is linked or related to another entity or activity.
  • E. successorAirline
    Indicates that one airline has taken over, replaced, or continued the operations of another airline as its successor.
  • F. None of above.

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_69d8b91104e08190a8241f7d260a5162 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4f7e287548190b666a990e5b168b0 completed April 19, 2026, 3:42 p.m.
PD Predicate disambiguation batch_69e4332336cc8190808b9c70c888ba65 completed April 19, 2026, 1:42 a.m.
Created at: April 10, 2026, 10:33 a.m.