Triple
T20917102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ardez |
E515099
|
entity |
| Predicate | usedLanguageTraditionally |
P42338
|
FINISHED |
| Object | Vallader dialect of 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: Vallader dialect of Romansh | Statement: [Ardez, usedLanguageTraditionally, Vallader dialect of Romansh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedLanguageTraditionally Context triple: [Ardez, usedLanguageTraditionally, Vallader dialect of Romansh]
-
A.
traditionalLanguageName
Indicates the name traditionally used in a particular language to refer to the subject entity.
-
B.
laterTraditionsLanguage
Indicates that later traditions or sources refer to or describe the subject using the specified language.
-
C.
languageFamilyTraditional
Indicates that one entity belongs to, or is classified under, the traditional language family of the other entity.
-
D.
hasTraditionalLanguageRegion
Indicates the geographic region traditionally associated with the use or origin of a particular language.
-
E.
typicalLanguages
chosen
Indicates the languages that are commonly or characteristically used, spoken, or associated with a given entity.
- 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_69e0b4f9d5ec8190bb2bd27350ed341c |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6ec635f4881909a560fb891100d8c |
completed | April 21, 2026, 3:17 a.m. |
| PD | Predicate disambiguation | batch_69e5c9ac91108190a6700fcdf2f11890 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:48 p.m.