Triple
T6987015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yeshimebet Ali |
E161988
|
entity |
| Predicate | placeOfOrigin |
P3743
|
FINISHED |
| Object | Shewa |
E455094
|
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: Shewa | Statement: [Yeshimebet Ali, placeOfOrigin, Shewa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shewa Context triple: [Yeshimebet Ali, placeOfOrigin, Shewa]
-
A.
Shewa
chosen
Shewa is a historic central region of Ethiopia that has played a major political and cultural role in the formation of the modern Ethiopian state.
-
B.
Abasha
Abasha is a small town in western Georgia’s Samegrelo region, known as a local administrative and cultural center.
-
C.
Shawiya
Shawiya refers to an Amazigh (Berber) ethnic group and their Zenati Berber language spoken primarily in the Aurès Mountains of northeastern Algeria.
-
D.
She'eb
She'eb is a town in Eritrea located within the Northern Red Sea administrative region.
-
E.
Wukro
Wukro is a town in northern Ethiopia known for its historic rock-hewn churches and its location along the main road in the Tigray Region.
- 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_69c68856d7808190ab33ee914640281b |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6db95c6148190bdb5f355ac04db3f |
completed | March 27, 2026, 7:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c761cfda14819088e11889f0151a37 |
completed | March 28, 2026, 5:06 a.m. |
Created at: March 27, 2026, 2:32 p.m.