Triple
T23060576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Formosan |
E574286
|
entity |
| Predicate | hasSubgroup |
P747
|
FINISHED |
| Object | Atayalic |
—
|
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: Atayalic | Statement: [Northern Formosan, hasSubgroup, Atayalic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Atayalic Context triple: [Northern Formosan, hasSubgroup, Atayalic]
-
A.
Atayalic languages
chosen
The Atayalic languages are a small subgroup of indigenous Austronesian languages spoken in northern Taiwan, primarily by the Atayal and Seediq peoples.
-
B.
Hocotatian
A Hocotatian is a tiny, spacefaring alien from the planet Hocotate featured in Nintendo’s Pikmin series.
-
C.
Taracahitic
Taracahitic is a proposed subgroup of the Uto-Aztecan language family that includes several indigenous languages once spoken in northwestern Mexico.
-
D.
Tepiman languages
The Tepiman languages are a group of closely related Uto-Aztecan indigenous languages spoken primarily in northern Mexico by various Tepehuán and Piman peoples.
-
E.
Curripaco language
The Curripaco language is an Arawakan language spoken by the Curripaco people of the Northwest Amazon region in Brazil, Colombia, and Venezuela.
- 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.