Triple
T21947640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isoko |
E541974
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Isoko 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: Isoko language | Statement: [Isoko, language, Isoko language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Isoko language Context triple: [Isoko, language, Isoko language]
-
A.
Isoko language
chosen
The Isoko language is a Niger-Congo language spoken primarily by the Isoko people of southern Nigeria, particularly in Delta State.
-
B.
Kioko language
The Kioko language is an Austronesian language of the Muna–Buton subgroup spoken by a small community in southeastern Sulawesi, Indonesia.
-
C.
Warihío language
The Warihío language is an indigenous Uto-Aztecan language spoken by the Warihío people of northwestern Mexico.
-
D.
Keiyo language
The Keiyo language is a Southern Nilotic language spoken by the Keiyo people of Kenya’s Rift Valley, closely associated with and linguistically similar to other Kalenjin languages such as Kipsigis.
-
E.
Sa’och language
The Sa’och language is an endangered Austroasiatic language spoken by the Sa’och people of Cambodia and Thailand, belonging to the Pearic branch.
- 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_69e0c47ef0e48190a50e1bcc43f4b3fd |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1243a2f788190bd4625fa79888696 |
completed | April 28, 2026, 9:18 p.m. |
Created at: April 16, 2026, 7:57 p.m.