Triple
T13804587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eastern Region of Uganda |
E331727
|
entity |
| Predicate | hasDistrict |
P459
|
FINISHED |
| Object | Mbale District |
E1020030
|
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: Mbale District | Statement: [Eastern Region of Uganda, hasDistrict, Mbale District]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mbale District Context triple: [Eastern Region of Uganda, hasDistrict, Mbale District]
-
A.
Mpigi District
Mpigi District is an administrative district in central Uganda known for its agricultural activities and proximity to the capital, Kampala.
-
B.
Mbale
chosen
Mbale is a major town in eastern Uganda, known as a commercial and administrative center near the slopes of Mount Elgon.
-
C.
Mubende District
Mubende District is an administrative district in central Uganda known for its agricultural activities and strategic location along major transport routes.
-
D.
Luweero District
Luweero District is an administrative district in Uganda known for its role as a key battleground area during the Ugandan Bush War in the 1980s.
-
E.
Kibaale District
Kibaale District is a rural administrative district in western Uganda known for its agriculture and forested landscapes.
- 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_69d81c59f8808190a851bc56afdc55e9 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de026c36108190a7436034a730a261 |
completed | April 14, 2026, 9:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b08db39c8190a76637b36b77d643 |
completed | May 3, 2026, 8:31 p.m. |
Created at: April 9, 2026, 10:12 p.m.