Triple
T17154146
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saho language |
E416298
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | Saho-Afar |
E416297
|
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: Saho-Afar | Statement: [Saho language, hasAlternativeName, Saho-Afar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saho-Afar Context triple: [Saho language, hasAlternativeName, Saho-Afar]
-
A.
Saho-Afar
chosen
Saho-Afar is an alternative name for the Saho language spoken primarily in Eritrea and neighboring regions.
-
B.
Saharidj
Saharidj is a town located in Bouira Province in northern Algeria.
-
C.
Sah
Sah is an ancient Egyptian god associated with the constellation Orion and often linked with the goddess Sopdet in celestial mythology.
-
D.
Tahaggart
Tahaggart is a regional variety of the Tuareg Berber language Tamasheq, spoken by Tuareg communities in parts of the central Sahara.
-
E.
Sarhili
Sarhili was a 19th-century Xhosa king of the Gcaleka who ruled during a period of intense conflict and colonial expansion in the Eastern Cape region of South Africa.
- 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_69d886d279c081909f8ff1f743ddeb69 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f4092c40819096359ff90af16c3e |
completed | April 18, 2026, 9:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a015fc46c308190b09efb13776747e7 |
completed | May 11, 2026, 4:49 a.m. |
Created at: April 10, 2026, 5:37 a.m.