Triple
T21917183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maputaland |
E541209
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Sodwana Bay |
—
|
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: Sodwana Bay | Statement: [Maputaland, contains, Sodwana Bay]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sodwana Bay Context triple: [Maputaland, contains, Sodwana Bay]
-
A.
Sodwana Bay
chosen
Sodwana Bay is a renowned coastal destination in South Africa famous for its rich marine biodiversity, coral reefs, and world-class scuba diving and snorkeling opportunities.
-
B.
Kosi Bay
Kosi Bay is a coastal lake system in northeastern KwaZulu-Natal, South Africa, renowned for its rich biodiversity, traditional fish traps, and unspoiled beaches near the Mozambique border.
-
C.
Mzima Springs
Mzima Springs is a series of natural freshwater springs in Kenya renowned for their clear waters, hippos, crocodiles, and underwater viewing platforms within Tsavo National Park.
-
D.
Zoombezi Bay
Zoombezi Bay is a popular outdoor water park in Ohio known for its water slides, wave pools, and family-friendly attractions.
-
E.
Tembe
Tembe is an indigenous language of the Tupi–Guaraní family spoken by the Tembé people of northern Brazil.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c47c4b9c8190a5586a75f5f36453 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1233858308190a877d8015db4d380 |
completed | April 28, 2026, 9:14 p.m. |
Created at: April 16, 2026, 7:43 p.m.