Triple
T23060076
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atayal language |
E574272
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object | S’uli Atayal |
—
|
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: S’uli Atayal | Statement: [Atayal language, hasDialect, S’uli Atayal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: S’uli Atayal Context triple: [Atayal language, hasDialect, S’uli Atayal]
-
A.
Mayrinax Atayal
chosen
Mayrinax Atayal is a major dialect of the Atayal language spoken by the Atayal Indigenous people of northern Taiwan.
-
B.
Hengchun Amis
Hengchun Amis is a dialect of the Amis language spoken by the Amis people in the Hengchun area of southern Taiwan.
-
C.
Amah Mutsun
Amah Mutsun are a Native American tribal community from the central California coast, traditionally associated with the Ohlone cultural and linguistic group and now active in cultural revitalization and land stewardship.
-
D.
Truku
Truku is an indigenous Taiwanese group recognized as a distinct subgroup of the Seediq people, known for its unique language variety and mountain-based cultural traditions.
-
E.
Suo-Gân
Suo-Gân is a traditional Welsh lullaby known for its gentle melody and soothing, lyrical character.
- 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_69e245ba7ae48190be606dbc54120e39 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1899f359081909e89e19db3833a3d |
completed | April 29, 2026, 4:31 a.m. |
Created at: April 17, 2026, 3:55 p.m.