Triple

T25996066
Position Surface form Disambiguated ID Type / Status
Subject Kamuzu International Airport E646488 entity
Predicate isOneOfMainAirportsIn P75084 FINISHED
Object Malawi NE NERFINISHED

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: Malawi | Statement: [Kamuzu International Airport, isOneOfMainAirportsIn, Malawi]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isOneOfMainAirportsIn
Context triple: [Kamuzu International Airport, isOneOfMainAirportsIn, Malawi]
  • A. isMainAirportStopFor
    Indicates that a given airport serves as the primary or principal stop for a specified route, service, or transportation connection.
  • B. isMajorRegionalAirportFor chosen
    Indicates that an airport serves as a primary or significant air travel hub for a particular region.
  • C. hasPrimaryAirportRole
    Indicates that an entity holds the main or principal functional role associated with an airport.
  • D. isOnlyInternationalAirportOf
    Indicates that an airport is the single, unique international airport serving a particular city, region, or country.
  • E. isLocatedAtAirportServingCity
    Indicates that something is situated at an airport that provides service to a particular city.
  • 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_69e77e88cb8481908da31d4a00661f55 completed April 21, 2026, 1:41 p.m.
NER Named-entity recognition batch_69f62d89b89c8190afb372a8172111e7 completed May 2, 2026, 4:59 p.m.
PD Predicate disambiguation batch_69f62c1379f08190836c3e02b0c892df completed May 2, 2026, 4:53 p.m.
Created at: April 22, 2026, 8:58 a.m.