Triple
T3827737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nadi–Vancouver |
E88731
|
entity |
| Predicate | servesCityRole |
P8234
|
FINISHED |
| Object | Fiji’s main tourism hub |
—
|
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: Fiji’s main tourism hub | Statement: [Nadi–Vancouver, servesCityRole, Fiji’s main tourism hub]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesCityRole Context triple: [Nadi–Vancouver, servesCityRole, Fiji’s main tourism hub]
-
A.
hasCityRole
chosen
Indicates that an entity holds or is assigned a specific role, function, or status within a particular city.
-
B.
servedCity
Indicates that a service, route, or facility operates in, reaches, or is available to a particular city.
-
C.
hasMajorCityRole
Indicates that an entity plays a significant official or functional role in the governance, administration, or key operations of a major city.
-
D.
cityServedRegion
Indicates that a city provides services to, or functions as an administrative or economic center for, a specified region.
-
E.
servesRole
Indicates that one entity performs, fulfills, or occupies a particular function, position, or responsibility in relation to another entity.
- 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_69aed9538cf881909d9ce8ca4ac7c18c |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeeb8459f881908a2c91bb07e381ef |
completed | March 9, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69aee74c2e04819094b94b3c0bac1806 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:17 p.m.