Triple
T10787158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Province, Zambia |
E254479
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object | Mazabuka |
E266996
|
NE 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: Mazabuka | Statement: [Southern Province, Zambia, containsTown, Mazabuka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mazabuka Context triple: [Southern Province, Zambia, containsTown, Mazabuka]
-
A.
Mazabuka
chosen
Mazabuka is a town in southern Zambia known for its sugar industry and agricultural production.
-
B.
Makuxi
Makuxi is an indigenous people of northern Brazil and neighboring regions, known for their distinct language, culture, and traditional practices in the Amazonian savanna.
-
C.
Makarora
Makarora is a small rural settlement in New Zealand’s South Island, known as a gateway to outdoor activities and hiking in the Southern Alps region.
-
D.
Kabaena
Kabaena is an island in Indonesia known for its location off the coast of Sulawesi and its mix of coastal and hilly landscapes.
-
E.
Ngqumbazi
Ngqumbazi was a Zulu royal woman best known as the mother of King Cetshwayo kaMpande of the Zulu Kingdom.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732d5422481908d7ab833c6cbc879 |
completed | April 9, 2026, 5:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69deb0c85d288190b13b1bc66921332c |
completed | April 14, 2026, 9:25 p.m. |
Created at: April 8, 2026, 9:17 p.m.