Triple
T7994181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Singida Region |
E186081
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Singida |
E693992
|
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: Singida | Statement: [Singida Region, capital, Singida]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Singida Context triple: [Singida Region, capital, Singida]
-
A.
Singida
chosen
Singida is a regional town in central Tanzania known as an important administrative and transport hub.
-
B.
Sanyati
Sanyati is a small town in Zimbabwe known for its agricultural activities and location within Mashonaland West Province.
-
C.
Kanyaga
"Kanyaga" is a popular Tanzanian Bongo Flava hit song by Diamond Platnumz known for its energetic beat and danceable style.
-
D.
Kiunga
Kiunga is a river port town in Western Province, Papua New Guinea, serving as a key commercial and transport hub on the Fly River.
-
E.
Nyazura
Nyazura is a small town in eastern Zimbabwe situated along the main road and railway linking Harare and Mutare.
- 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_69ca829c6c308190ab05b43d234c52b2 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c73ba388190bcedc29fbdd22f3c |
completed | March 31, 2026, 3:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe105d400819096ba271416bb24e7 |
completed | March 31, 2026, 2:58 p.m. |
Created at: March 30, 2026, 5:16 p.m.