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.