Triple
T29979324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kamang people |
E761536
|
entity |
| Predicate | linguisticVitality |
P152598
|
FINISHED |
| Object | vulnerable |
—
|
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: vulnerable | Statement: [Kamang people, linguisticVitality, vulnerable]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linguisticVitality Context triple: [Kamang people, linguisticVitality, vulnerable]
-
A.
languageVitality
chosen
Indicates the degree to which a language is actively used, maintained, and transmitted within a community, reflecting its risk of endangerment or extinction.
-
B.
linguisticVariation
Indicates a relationship where one linguistic form differs from another in expression, usage, or structure while remaining related in meaning or function.
-
C.
languageDiversity
Indicates the degree to which multiple distinct languages are present and used within a given context or population.
-
D.
languageEcology
Indicates the relationship between a language and its surrounding social, cultural, and environmental context, including how it interacts with and is influenced by other languages and communicative practices.
-
E.
endangeredLanguage
Indicates that a language is at risk of falling out of use and potentially becoming extinct due to having too few active speakers or insufficient intergenerational transmission.
- 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_69f2246851148190b8e76206db94b105 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f678d75b1c81909dfc607a4bba5826 |
completed | May 2, 2026, 10:21 p.m. |
| PD | Predicate disambiguation | batch_69f66ec9919881908a187bfc7c4df192 |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 29, 2026, 6:34 p.m.