Triple
T23265939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tʷaχə |
E588146
|
entity |
| Predicate | autonymFor |
P1435
|
FINISHED |
| Object | Ubykh language |
—
|
NE NERFINISHED |
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: Ubykh language | Statement: [Tʷaχə, autonymFor, Ubykh language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ubykh language Context triple: [Tʷaχə, autonymFor, Ubykh language]
-
A.
Ubykh
chosen
Ubykh is an extinct Northwest Caucasian language once spoken along the eastern Black Sea coast, renowned for its exceptionally large consonant inventory and minimal vowel system.
-
B.
Siwi language
The Siwi language is a Berber (Amazigh) language spoken by the Siwi people in Egypt’s Siwa Oasis, characterized by significant Arabic influence and its status as one of the easternmost Berber languages.
-
C.
Soqotri language
The Soqotri language is a Modern South Arabian Semitic language spoken primarily by the indigenous people of the island of Socotra in Yemen.
-
D.
Ebira language
Ebira language is a Nupoid language of the Niger-Congo family spoken primarily by the Ebira people in central Nigeria.
-
E.
Semaq Beri language
Semaq Beri is an Aslian Austroasiatic language spoken by the indigenous Semaq Beri people of Peninsular Malaysia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e25d148adc819088efbf42672604e9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f194cc3b908190aaefd036aa2b52b5 |
completed | April 29, 2026, 5:19 a.m. |
Created at: April 17, 2026, 4:35 p.m.