Triple
T23406986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rukai people |
E559960
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Rukai 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: Rukai language | Statement: [Rukai people, language, Rukai language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rukai language Context triple: [Rukai people, language, Rukai language]
-
A.
Rukai language
chosen
The Rukai language is an Austronesian language spoken by the Rukai people of southern Taiwan, known for its complex phonology and rich system of honorifics.
-
B.
Red Tai language
The Red Tai language is a Southwestern Tai language spoken by the Red Tai ethnic group in parts of Vietnam and Laos, closely related to other Tai languages such as Black Tai.
-
C.
Batui language
The Batui language is an Austronesian language spoken in Central Sulawesi, Indonesia, and is part of the Saluan–Banggai subgroup.
-
D.
Kavalan language
The Kavalan language is an endangered Austronesian language of the indigenous Kavalan people of northeastern Taiwan.
-
E.
Truku language
The Truku language is an indigenous Austronesian language of the Truku people in eastern Taiwan, noted for its complex phonology and endangered status.
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a50e607c8190ba0a22e89862a2d9 |
completed | April 29, 2026, 6:28 a.m. |
Created at: April 17, 2026, 5:38 p.m.