Triple
T22849652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ersuic peoples |
E566322
|
entity |
| Predicate | speaks |
P741
|
FINISHED |
| Object | Duoxu 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: Duoxu language | Statement: [Ersuic peoples, speaks, Duoxu language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Duoxu language Context triple: [Ersuic peoples, speaks, Duoxu language]
-
A.
Duoxu language
chosen
The Duoxu language is an endangered Qiangic language of the Sino-Tibetan family once spoken by a small ethnic community in Sichuan, China.
-
B.
Duupa language
Duupa language is a lesser-known Niger-Congo language spoken by the Duupa people in northern Cameroon.
-
C.
Longgu language
The Longgu language is an Oceanic language spoken by communities in the Solomon Islands, belonging to the Southeast Solomonic branch of the Austronesian language family.
-
D.
Dobel language
The Dobel language is an Austronesian language spoken by the Aru Islands community in eastern Indonesia.
-
E.
Sanqiao language
The Sanqiao language is a lesser-known Kam–Sui language of the Tai–Kadai family spoken by the Sanqiao people in parts of southern China.
- 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_69e2458750b481908a8e4cf4609cc6cf |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17eb74700819090d191b3a7a17034 |
completed | April 29, 2026, 3:44 a.m. |
Created at: April 17, 2026, 3:36 p.m.