Triple
T13974256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Faleolo International Airport |
E336142
|
entity |
| Predicate | servesAsMainEntryPointFor |
P10516
|
FINISHED |
| Object | tourism in Samoa |
—
|
LITERAL FINISHED |
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: tourism in Samoa | Statement: [Faleolo International Airport, servesAsMainEntryPointFor, tourism in Samoa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesAsMainEntryPointFor Context triple: [Faleolo International Airport, servesAsMainEntryPointFor, tourism in Samoa]
-
A.
entryPointFor
Indicates that one entity serves as the access or starting location through which another entity is entered, initiated, or reached.
-
B.
mainStartingPoint
Indicates the primary location or position from which an event, process, or path begins.
-
C.
isServedFor
Indicates that something is provided or presented as suitable or intended for a particular purpose, use, or recipient.
-
D.
servesAsGatewayTo
chosen
Indicates that one entity functions as an entry point, access route, or intermediary channel that enables reaching or connecting to another entity.
-
E.
typicallyServedAs
Indicates that something is most commonly presented, used, or offered in a particular role, form, or function.
- 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_69d81c61f3508190aaf2ca0dc0002c59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e8fd6d48190a157eae8df3a2f3a |
completed | April 14, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69dd465a21408190b912a42c50ffa0d9 |
completed | April 13, 2026, 7:39 p.m. |
Created at: April 9, 2026, 10:18 p.m.