Triple
T24583345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sirionó language |
E608310
|
entity |
| Predicate | isSubjectToLanguageShift |
P99457
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Sirionó language, isSubjectToLanguageShift, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSubjectToLanguageShift Context triple: [Sirionó language, isSubjectToLanguageShift, yes]
-
A.
languageShift
Indicates a change in the primary language used by an entity, such as switching from one language to another over time or in a given context.
-
B.
isLanguageOf
Indicates that a particular language is used as the official or primary language associated with a given entity (such as a person, document, or region).
-
C.
riskOfLanguageShift
chosen
Indicates that there is a likelihood or tendency for one language to be replaced or significantly reduced in use by another within a given community or context.
-
D.
usesLanguageFor
Indicates that an entity employs a particular language as a tool or medium to perform some activity, function, or purpose.
-
E.
languageAffected
Indicates that one entity has an impact on, modifies, or influences the characteristics, usage, or status of a language.
- 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_69e2c4ce89248190ad99e18f0638dfbb |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a984577881908c855f5e05756909 |
completed | April 30, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f2a6c1f07081908edf0b521767e79b |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:29 a.m.