Triple
T11788942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romansh people |
E280340
|
entity |
| Predicate | mainContactLanguage |
P46872
|
FINISHED |
| Object | German |
—
|
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: German | Statement: [Romansh people, mainContactLanguage, German]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainContactLanguage Context triple: [Romansh people, mainContactLanguage, German]
-
A.
primaryLanguageContact
chosen
Indicates that one language serves as the main or dominant medium of communication in a particular contact situation between language communities.
-
B.
primaryLanguageOf
Indicates that a specified language is the main or official language used by a particular entity (such as a person, organization, or region).
-
C.
parentLanguage
Indicates that one language is the ancestral or source language from which another language is derived or historically developed.
-
D.
identityLanguage
Indicates that two language entities are identical or represent the same language.
-
E.
primaryLanguageType
Indicates the main category or kind of language (such as spoken, written, or signed) that serves as the primary mode of communication in a given context or for 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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a587c2d881909297c3a6c7d26080 |
completed | April 10, 2026, 7:23 a.m. |
| PD | Predicate disambiguation | batch_69d8a2491f048190853239bc05090bf4 |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:42 p.m.