Triple
T10650389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barotseland |
E250951
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Mongu |
E340711
|
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: Mongu | Statement: [Barotseland, capital, Mongu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mongu Context triple: [Barotseland, capital, Mongu]
-
A.
Mongu
chosen
Mongu is a town in western Zambia that serves as the administrative and cultural center of the Lozi people and a key hub near the Zambezi River’s Barotse Floodplain.
-
B.
Mpulungu
Mpulungu is a Zambian port town that serves as the country’s main access point to Lake Tanganyika and a hub for regional fishing and trade.
-
C.
Gcaleka
Gcaleka is a prominent royal clan of the Xhosa people, historically associated with leadership and the Gcaleka sub-group in the Eastern Cape region of South Africa.
-
D.
Ngazidja
Ngazidja, also known as Grande Comore, is the largest island of the Comoros archipelago in the Indian Ocean and home to the nation’s capital.
-
E.
Molefe
Molefe is a Southern African surname commonly found among Tswana- and Sotho-speaking communities.
- 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_69d6aa5a4c4881908f39be6efe5981e5 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6dfe4b97081908815b77612222318 |
completed | April 8, 2026, 11:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d988530f288190b8150d159f723a74 |
completed | April 10, 2026, 11:31 p.m. |
Created at: April 8, 2026, 9:06 p.m.