Triple
T22931875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Subiya language |
E569463
|
entity |
| Predicate | glottologName |
P6521
|
FINISHED |
| Object | Subiya |
—
|
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: Subiya | Statement: [Subiya language, glottologName, Subiya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Subiya Context triple: [Subiya language, glottologName, Subiya]
-
A.
Subiya
chosen
Subiya is a Bantu language spoken by the Subiya people primarily in the Zambezi (Caprivi) region of Namibia and surrounding areas of southern Africa.
-
B.
Subiyah
Subiyah is a sparsely populated area in northern Kuwait, located on the north shore of Kuwait Bay and known for its strategic position and development projects linked to major infrastructure like the Sheikh Jaber Al-Ahmad Al-Sabah Causeway.
-
C.
Asharh
Asharh is a monsoon-season month in the Bengali calendar, typically spanning late June to mid-July in the Gregorian calendar.
-
D.
Saatly
Saatly is a town and the administrative center of the Saatly District located in central Azerbaijan.
-
E.
Batahari
Batahari is an alternative name for the Bathari language, a critically endangered Modern South Arabian language spoken by a small community in Oman.
- 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_69e2458f7d008190901dccbaebeaba24 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1813260608190bb9e1ca704c7e12f |
completed | April 29, 2026, 3:55 a.m. |
Created at: April 17, 2026, 3:44 p.m.