Triple
T6364037
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ubykhs |
E143180
|
entity |
| Predicate | dateOfLanguageExtinction |
P43860
|
FINISHED |
| Object | 1992 |
—
|
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: 1992 | Statement: [Ubykhs, dateOfLanguageExtinction, 1992]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateOfLanguageExtinction Context triple: [Ubykhs, dateOfLanguageExtinction, 1992]
-
A.
extinctionDate
Indicates the date or time at which an entity (typically a species or lineage) ceased to exist.
-
B.
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.
-
C.
languageEndangermentStatus
Indicates the degree to which a language is at risk of falling out of use or becoming extinct.
-
D.
extinctionPeriod
Indicates the time span during which an entity ceases to exist or is considered extinct.
-
E.
languageEndangermentFactors
Indicates the various social, political, economic, and cultural conditions that contribute to a language becoming vulnerable, endangered, or extinct.
- 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_69c008d8c61081908bcaf61510d881ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0680d51a4819098a6bcd3dfd73be4 |
completed | March 22, 2026, 10:07 p.m. |
| PD | Predicate disambiguation | batch_69c060ee055081908c79a1d151bd74cd |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:32 p.m.