Triple
T16365289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kistane language |
E397420
|
entity |
| Predicate | alternativeName |
P39
|
FINISHED |
| Object | Soddo language |
E397417
|
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: Soddo language | Statement: [Kistane language, alternativeName, Soddo language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Soddo language Context triple: [Kistane language, alternativeName, Soddo language]
-
A.
Soddo language
chosen
The Soddo language is an Afroasiatic Semitic language spoken by the Soddo Gurage people of central Ethiopia.
-
B.
Sidama language
The Sidama language is a Cushitic language spoken primarily by the Sidama people in southern Ethiopia.
-
C.
Obudu language
Obudu language is an indigenous language spoken by the Obudu people of southeastern Nigeria, belonging to the Niger-Congo language family.
-
D.
Datooga language
The Datooga language is a Southern Nilotic language spoken by the Datooga people of north-central Tanzania, known for its complex dialect diversity and rich oral tradition.
-
E.
Gafat language
The Gafat language is an extinct South Ethiopic Semitic language once spoken in Ethiopia, closely related to Harari and derived from the ancient Ge'ez linguistic tradition.
- 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_69d87f2778dc8190aa95c7572db127e6 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2ff3c915c81909e1757fc31921876 |
completed | April 18, 2026, 3:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002dc0b3d4819089e6fba536ec8a11 |
completed | May 10, 2026, 7:03 a.m. |
Created at: April 10, 2026, 5:08 a.m.