Triple
T21665114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Malawi |
E534692
|
entity |
| Predicate | hasUrbanCenter |
P2106
|
FINISHED |
| Object | Chikwawa |
—
|
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: Chikwawa | Statement: [Southern Malawi, hasUrbanCenter, Chikwawa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chikwawa Context triple: [Southern Malawi, hasUrbanCenter, Chikwawa]
-
A.
Chikwawa
chosen
Chikwawa is a town in southern Malawi known for its proximity to the Shire River and its role as an agricultural and trading center in the Lower Shire Valley.
-
B.
Thyolo
Thyolo is a town in southern Malawi known as an important center of the country’s tea-growing region.
-
C.
Lilongwe
Lilongwe is the largest city and administrative and political center of Malawi, located in the country’s central region.
-
D.
Kapiri Mposhi
Kapiri Mposhi is a town in central Zambia that serves as a key rail and road junction linking the country to Tanzania and other regions.
-
E.
Zomba
Zomba is a historic city in southern Malawi that served as the country’s former capital and remains an important administrative and educational center.
- 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_69e0c467e1f48190af2650b19175abc4 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef6c0b26c8819092c13e59dcc3c25c |
completed | April 27, 2026, 2 p.m. |
Created at: April 16, 2026, 6:36 p.m.