Triple
T4686423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | uShaka Marine World |
E103930
|
entity |
| Predicate | regionTourismRole |
P52358
|
FINISHED |
| Object | major Durban tourist destination |
—
|
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: major Durban tourist destination | Statement: [uShaka Marine World, regionTourismRole, major Durban tourist destination]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionTourismRole Context triple: [uShaka Marine World, regionTourismRole, major Durban tourist destination]
-
A.
tourismRegion
Indicates that a place or area is designated or recognized as a tourism region associated with another geographic or administrative entity.
-
B.
primaryTourismHub
chosen
Indicates that a location serves as the main center or focal point for tourism activities within a given area or region.
-
C.
tourismType
Indicates the specific category or kind of tourism activity or experience associated with an entity.
-
D.
tourismAssociation
Indicates that there is an organizational or formal association related to tourism activities, services, or promotion between the involved entities.
-
E.
tourismFrom
Indicates that tourists or visitor activity originates from one place and is directed toward another location.
- 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_69bd43debbf08190b4bc372e286ec234 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd66059bfc8190885d26d05dd38df1 |
completed | March 20, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69bd6219da948190bbbb50f08573ab4d |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:16 p.m.