Triple
T19732729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maniema Province |
E473894
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Kindu |
—
|
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: Kindu | Statement: [Maniema Province, capital, Kindu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kindu Context triple: [Maniema Province, capital, Kindu]
-
A.
Kindu
chosen
Kindu is a city in the eastern Democratic Republic of the Congo that serves as the capital of Maniema Province and an important regional transport hub.
-
B.
Kunda
Kunda is a small industrial town in northern Estonia known for its cement industry and archaeological significance.
-
C.
Kunda
Kunda is the sacred stepped water tank associated with the Modhera Sun Temple in Gujarat, India, used historically for ritual bathing and religious ceremonies.
-
D.
Sere Kunda
Sere Kunda is the largest urban center and commercial hub of The Gambia, located near the capital city of Banjul.
-
E.
Karume
Karume is a Swahili surname most prominently associated with Abeid Karume, the first president of Zanzibar and a key figure in Tanzanian political history.
- 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e651596b98819090bcaf05c7b74555 |
completed | April 20, 2026, 4:16 p.m. |
Created at: April 10, 2026, 1:47 p.m.