Triple
T8094430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sauda |
E188946
|
entity |
| Predicate | usesWrittenStandard |
P1587
|
FINISHED |
| Object | Nynorsk |
E92855
|
NE 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: Nynorsk | Statement: [Sauda, usesWrittenStandard, Nynorsk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nynorsk Context triple: [Sauda, usesWrittenStandard, Nynorsk]
-
A.
Nynorsk
chosen
Nynorsk is one of the two official written standards of the Norwegian language, based primarily on rural and western Norwegian dialects.
-
B.
Middle Norwegian
Middle Norwegian is a historical North Germanic language stage spoken in Norway roughly between the late Middle Ages and the early modern period, bridging Old Norwegian and modern Norwegian.
-
C.
New Norwegian
New Norwegian is one of the two official written standards of the Norwegian language, developed in the 19th century from rural Norwegian dialects.
-
D.
Norwegian language
Norwegian is a North Germanic language spoken primarily in Norway, closely related to Danish and Swedish and featuring two official written standards, Bokmål and Nynorsk.
-
E.
Bokmål
Bokmål is the most widely used written standard of the Norwegian language, employed in government, education, media, and everyday communication.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca82b7b3e88190b9041ab0ef28b3cb |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb429089cc81909e4625f9cc7e305f |
completed | March 31, 2026, 3:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc64112138819096050975d707d8ee |
completed | April 1, 2026, 12:17 a.m. |
Created at: March 30, 2026, 5:30 p.m.