Triple
T38497708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Swati |
E919738
|
entity |
| Predicate | isDialectOfLanguageWithName |
P73835
|
FINISHED |
| Object | siSwati |
—
|
NE NERFINISHED |
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: siSwati | Statement: [Southern Swati, isDialectOfLanguageWithName, siSwati]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isDialectOfLanguageWithName Context triple: [Southern Swati, isDialectOfLanguageWithName, siSwati]
-
A.
consideredDialectOf
chosen
Indicates that one language variety is regarded as a dialect of another language or linguistic standard.
-
B.
isDialectalBaseOf
Indicates that one language variety serves as the primary dialectal source or foundation from which another dialect develops or is derived.
-
C.
possiblyDialectOf
Indicates that one language variety may be a dialect of another, but this relationship is uncertain or not definitively established.
-
D.
hasPrimaryLanguageDialect
Indicates that an entity’s main or default language is a specific dialect of a broader language.
-
E.
isLanguageOf
Indicates that a particular language is used as the official or primary language associated with a given entity (such as a person, document, or region).
- 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_69f76e9ddd4481908f8c04439d848f9d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:31 p.m.