Triple
T23060333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Amis |
E574279
|
entity |
| Predicate | hasDialectGroupRole |
P92238
|
FINISHED |
| Object | major dialect of Amis |
—
|
LITERAL FINISHED |
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: major dialect of Amis | Statement: [Central Amis, hasDialectGroupRole, major dialect of Amis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDialectGroupRole Context triple: [Central Amis, hasDialectGroupRole, major dialect of Amis]
-
A.
isDialectGroupOf
chosen
Indicates that one linguistic variety is a dialect group or cluster belonging to a broader language or language family.
-
B.
associatedWithDialectGroup
Indicates that one entity is connected or related to a particular dialect group, typically through usage, origin, or classification.
-
C.
hasMajorDialectGroup
Indicates that an entity (typically a language) is associated with a primary or major dialect group to which it belongs.
-
D.
hasDialectCluster
Indicates that one language or linguistic variety is associated with a particular group or cluster of related dialects.
-
E.
commonInDialectGroup
Indicates that something (such as a word, form, or feature) is frequently used or widely found within a particular dialect group.
- F. None of above.
Provenance (3 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. |
| PD | Predicate disambiguation | batch_69ef89d5f71881908b9f9d0c8aab278c |
completed | April 27, 2026, 4:07 p.m. |
Created at: April 17, 2026, 3:55 p.m.