Triple
T8860629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oromia Region |
E210877
|
entity |
| Predicate | majorCity |
P316
|
FINISHED |
| Object | Jimma |
E753691
|
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: Jimma | Statement: [Oromia Region, majorCity, Jimma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jimma Context triple: [Oromia Region, majorCity, Jimma]
-
A.
Jimma
chosen
Jimma is a city in southwestern Ethiopia known as a major center of coffee production and regional trade.
-
B.
Jhelumi
Jhelumi is a regional dialect of the Potohari language spoken primarily in and around the Jhelum area of Pakistan.
-
C.
Gujba
Gujba is a local government area and town in northeastern Nigeria, known for its predominantly rural communities and location within Yobe State.
-
D.
Harar Jugol
Harar Jugol is the historic walled city of Harar in eastern Ethiopia, renowned for its dense maze of alleyways, rich Islamic heritage, and distinctive traditional architecture.
-
E.
Banawali
Banawali is an archaeological site in Haryana, India, known for its well-preserved remains of the Indus Valley Civilization, including planned settlements and distinctive Harappan artifacts.
- 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_69ca838bbddc8190ab546d737e5d350f |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60e712d08190bfb1c4ba3acaea90 |
completed | April 1, 2026, 12:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfa0b94f5481909902b5fa405a502f |
completed | April 3, 2026, 11:12 a.m. |
Created at: March 30, 2026, 6:50 p.m.