Triple

T10413262
Position Surface form Disambiguated ID Type / Status
Subject EgyptAir Flight 990 E245447 entity
Predicate destinationAirportCode P16154 FINISHED
Object CAI E142329 NE FINISHED

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: CAI | Statement: [EgyptAir Flight 990, destinationAirportCode, CAI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CAI
Context triple: [EgyptAir Flight 990, destinationAirportCode, CAI]
  • A. CAI chosen
    CAI is the three-letter IATA airport code for Cairo International Airport, the main international gateway to Cairo, Egypt.
  • B. CAE
    CAE (Computer-Aided Engineering) is the use of computer software to simulate, analyze, and optimize engineering designs and processes.
  • C. CAE
    CAE is the IATA airport code for Columbia Metropolitan Airport, the primary commercial airport serving Columbia, South Carolina.
  • D. CAE
    CAE is a Canadian multinational company specializing in simulation and training solutions, particularly for civil aviation, defense, and healthcare industries.
  • E. CADE
    CADE is a leading international conference focused on research and advances in automated reasoning and automated theorem proving.
  • 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: destinationAirportCode
Context triple: [EgyptAir Flight 990, destinationAirportCode, CAI]
  • A. destinationAirportOfHijackedFlight
    Indicates the airport that served or was intended to serve as the destination of a hijacked flight.
  • B. typicalDestinationAirportIATA
    Indicates the IATA airport code that is typically the destination in this kind of trip or route.
  • C. destinationOfFlight chosen
    Indicates the location or place to which a given flight is traveling or scheduled to arrive.
  • D. destinationCity
    Indicates the city to which an entity is traveling, being sent, or ultimately directed.
  • E. destinationAirportAtTimeOfCrash
    Indicates the airport that was the intended destination of a flight at the time the crash occurred.
  • F. None of above.

Provenance (4 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_69d381be340c8190b05998703d42d224 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4ea0ec6fc8190a71af759226a3cba completed April 7, 2026, 11:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7fc043074819083d219ec1c40f931 completed April 9, 2026, 7:20 p.m.
PD Predicate disambiguation batch_69d4dfb6f160819090040644a12395ec completed April 7, 2026, 10:43 a.m.
Created at: April 6, 2026, 12:10 p.m.