Triple
T26464422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MANDARIN |
E665720
|
entity |
| Predicate | operatorHubAirport |
P4364
|
FINISHED |
| Object | Taiwan Taoyuan International Airport |
—
|
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: Taiwan Taoyuan International Airport | Statement: [MANDARIN, operatorHubAirport, Taiwan Taoyuan International Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatorHubAirport Context triple: [MANDARIN, operatorHubAirport, Taiwan Taoyuan International Airport]
-
A.
operatesAirport
Indicates that one entity manages and runs the operations of an airport.
-
B.
airlineHub
chosen
Indicates that a particular location (typically an airport or city) serves as a central hub or primary operational base for an airline.
-
C.
operatorMainHubAirportCountry
Indicates that an operator’s primary hub airport is located in the specified country.
-
D.
airportUse
Indicates that an airport is used or utilized by a particular entity, such as an airline, organization, or service.
-
E.
airportTypeManaged
Indicates that an entity is responsible for managing or overseeing a particular type or category of airport.
- 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_69ee883e812c8190a9b5a9cdb87fee5e |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69fd474b7e788190a9bb9b542d878f60 |
completed | May 8, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69fd46d8b2f0819099d92d72c902f60e |
completed | May 8, 2026, 2:13 a.m. |
Created at: April 27, 2026, 12:15 a.m.