Triple
T11349509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yoweri Museveni |
E268803
|
entity |
| Predicate | languageSpoken |
P151
|
FINISHED |
| Object | Runyankole |
E275007
|
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: Runyankole | Statement: [Yoweri Museveni, languageSpoken, Runyankole]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Runyankole Context triple: [Yoweri Museveni, languageSpoken, Runyankole]
-
A.
Runyankole
chosen
Runyankole is a Bantu language spoken primarily by the Banyankole people in southwestern Uganda.
-
B.
Mufulira
Mufulira is a mining town in northern Zambia known for its large copper mines and role in the country's Copperbelt region.
-
C.
Soroti
Soroti is a town in eastern Uganda that serves as a regional commercial and administrative center.
-
D.
Butiama
Butiama is a village in northern Tanzania best known as the birthplace and hometown of the country’s founding president, Julius Nyerere.
-
E.
Bukoto
Bukoto is a residential and commercial neighborhood in Kampala, Uganda, known for its mix of middle-class housing, local businesses, and proximity to several of the city’s prominent suburbs.
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7ea23391c819089e8f9725cb3a0ff |
completed | April 9, 2026, 6:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5b7d91168819096823e59a63ec24d |
completed | April 20, 2026, 5:21 a.m. |
Created at: April 8, 2026, 9:33 p.m.