Triple
T6584557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harar Province |
E159187
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object | Dire Dawa |
E599544
|
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: Dire Dawa | Statement: [Harar Province, hasCity, Dire Dawa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dire Dawa Context triple: [Harar Province, hasCity, Dire Dawa]
-
A.
Dire Dawa
chosen
Dire Dawa is one of Ethiopia’s largest and most important cities, serving as a major commercial and transportation hub in the eastern part of the country.
-
B.
Ras Dejen
Ras Dejen is the highest mountain in Ethiopia, located in the Simien Mountains and known for its dramatic highland scenery.
-
C.
Segeju
Segeju is a Bantu language of the Sabaki group spoken by the Segeju people in parts of coastal Kenya and Tanzania.
-
D.
Yared
Yared is a surname most notably associated with Gabriel Yared, the acclaimed Lebanese-French composer known for his film scores.
-
E.
Yared
Yared is a revered Ethiopian saint and composer traditionally credited with creating the sacred music and chant system of the Ethiopian Orthodox Church.
- 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_69c688366ce8819083f8883983c0df92 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6aeacbde08190a2e4e82cd12bc43f |
completed | March 27, 2026, 4:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6d576ab288190ac7e7b58e974697c |
completed | March 27, 2026, 7:07 p.m. |
Created at: March 27, 2026, 1:54 p.m.