Triple
T10390041
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eyak |
E244865
|
entity |
| Predicate | lastNativeSpeakerDied |
P43860
|
FINISHED |
| Object | 2008 |
—
|
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: 2008 | Statement: [Eyak, lastNativeSpeakerDied, 2008]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastNativeSpeakerDied Context triple: [Eyak, lastNativeSpeakerDied, 2008]
-
A.
lastNativeSpeakersDiedOut
chosen
Indicates that the final remaining native speakers of a language or dialect have died, resulting in the loss of native speech for that language.
-
B.
lastTraditionalNativeSpeakerOftenCitedAs
Indicates that the subject is widely regarded or referenced as the last traditional native speaker of the language or dialect in question.
-
C.
hasNoNativeSpeakers
Indicates that the language or dialect is not natively acquired as a first language by any living community.
-
D.
hasApproximateNativeSpeakers
Indicates that an entity is associated with an estimated or approximate number of people who speak it as their native language.
-
E.
historicallySpokenIn
Indicates that a language was used for spoken communication in a particular place or region during a past historical period.
- 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9b4f7d08190bcb16d3b4c8f22ad |
completed | April 7, 2026, 11:25 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb0e7a88190bec0b7a52c70dfe2 |
completed | April 7, 2026, 10:42 a.m. |
Created at: April 6, 2026, 12:05 p.m.