Triple
T598348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kiliwa language |
E11436
|
entity |
| Predicate | endangerment |
P16824
|
FINISHED |
| Object | very few fluent speakers |
—
|
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: very few fluent speakers | Statement: [Kiliwa language, endangerment, very few fluent speakers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endangerment Context triple: [Kiliwa language, endangerment, very few fluent speakers]
-
A.
threatenedBy
Indicates that one entity poses a danger or potential harm to another entity.
-
B.
areEndangeredIn
Indicates that the entities are classified as endangered within a specified geographic area or jurisdiction.
-
C.
threat
Indicates a relationship where one entity expresses or poses potential harm, danger, or negative consequences toward another entity.
-
D.
hazardType
Indicates the specific kind or category of hazard associated with an entity or situation.
-
E.
extinctionReason
Indicates the cause or factor responsible for an entity’s extinction.
- F. None of above. chosen
Provenance (4 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_69a4932779b881908688590d59c71900 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49dc4f7d08190990f70b9b3af6ce5 |
completed | March 1, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69a49cf59cd0819084e67981cb371e25 |
completed | March 1, 2026, 8:09 p.m. |
| PDg | Predicate description generation | batch_69a49dc0e6a08190b81d82a6f2571c41 |
completed | March 1, 2026, 8:12 p.m. |
Created at: March 1, 2026, 7:35 p.m.