Triple
T23271150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Standard Ndonga |
E588292
|
entity |
| Predicate | isOfficialFormOf |
P97338
|
FINISHED |
| Object | Ndonga dialect |
—
|
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: Ndonga dialect | Statement: [Standard Ndonga, isOfficialFormOf, Ndonga dialect]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOfficialFormOf Context triple: [Standard Ndonga, isOfficialFormOf, Ndonga dialect]
-
A.
isOfficialLanguageFormFor
chosen
Indicates that one language form is the officially recognized or standard variant used for another language or linguistic entity.
-
B.
isOfficialOfficeOf
Indicates that one entity serves as the formally recognized office or headquarters associated with another entity.
-
C.
isRealFormOf
Indicates that one entity is the actual, physically existing or fully realized version of another entity, which may be abstract, conceptual, or a representation.
-
D.
isOfficialOrganOf
Indicates that one entity serves as the formally designated organ, body, or institutional component of another entity within an official or legal structure.
-
E.
isOfficial
Indicates that an entity holds formal, authorized, or government-recognized status in a given context.
- 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_69e25d148adc819088efbf42672604e9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1957418fc819085ee528622e0c6de |
completed | April 29, 2026, 5:21 a.m. |
| PD | Predicate disambiguation | batch_69effcecabd88190856fb6e1d993e4dd |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:45 p.m.