Triple
T26513611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faaʻa International Airport |
E669753
|
entity |
| Predicate | mainInternationalGatewayFor |
P6759
|
FINISHED |
| Object | Tahiti |
—
|
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: Tahiti | Statement: [Faaʻa International Airport, mainInternationalGatewayFor, Tahiti]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainInternationalGatewayFor Context triple: [Faaʻa International Airport, mainInternationalGatewayFor, Tahiti]
-
A.
isMajorInternationalGatewayFor
chosen
Indicates that one entity serves as a primary, globally significant access point or hub for another entity’s international connections or flows.
-
B.
onInternationalRoute
Indicates that something (such as a service, vehicle, or connection) operates on or is part of a route that crosses international borders.
-
C.
isInternational
Indicates that something has a connection to, involves, or extends across more than one country.
-
D.
handlesInternationalTrafficAt
Indicates that an entity manages or processes international traffic at a specified location or facility.
-
E.
hasInternationalLink
Indicates that there exists a connection or association between entities that crosses national boundaries or involves multiple countries.
- 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_69eeb31b6dcc8190b30632dc3928a0c0 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61f12b0f08190bc4a16907941864c |
completed | May 2, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69f61b3a8ae0819090189fbd8eb19f2f |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 1:22 a.m.