Triple
T5001114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viafiers federalas svizras |
E112373
|
entity |
| Predicate | languageVariantOfName |
P5595
|
FINISHED |
| Object | Romansh |
—
|
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: Romansh | Statement: [Viafiers federalas svizras, languageVariantOfName, Romansh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageVariantOfName Context triple: [Viafiers federalas svizras, languageVariantOfName, Romansh]
-
A.
languageVariant
chosen
Indicates that one language is a variant, dialect, or localized form of another language.
-
B.
linguisticVariant
Indicates that one linguistic form is an alternative version or expression of another within the same or closely related language context.
-
C.
hasOfficialNameVariant
Indicates that an entity has an alternative official form or version of its name.
-
D.
regionalVariantOf
Indicates that one entity is a version or form of another that is specific to a particular geographic region or locale.
-
E.
originalPublicationLanguageVariant
Indicates that one language is a specific variant or version of the language in which a work was originally published.
- 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_69bd4432b32c81909f3b3c6bd10f0653 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7472a1dc8190942f568a81fdd961 |
completed | March 20, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69bd714aee2481908fb0dd5fa2daf3a1 |
completed | March 20, 2026, 4:09 p.m. |
Created at: March 20, 2026, 1:34 p.m.