Triple
T27313147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Provençal |
E689261
|
entity |
| Predicate | glottonym |
P6521
|
FINISHED |
| Object | provençau |
—
|
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: provençau | Statement: [Provençal, glottonym, provençau]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: glottonym Context triple: [Provençal, glottonym, provençau]
-
A.
glottoCategory
Indicates the linguistic classification or type (such as language family, subgroup, or category) to which a language or dialect is assigned.
-
B.
glottocode
Indicates the standardized Glottolog code that uniquely identifies the language or dialect associated with an entity.
-
C.
hasGlottologName
chosen
Indicates that an entity is associated with a specific name as recorded in the Glottolog linguistic database.
-
D.
lexifierLanguage
Indicates that one language serves as the primary source or base language from which the core vocabulary and structure of another language, typically a pidgin or creole, are derived.
-
E.
hasGlottologEntry
Indicates that there exists a corresponding entry for the entity in the Glottolog linguistic database.
- 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_69ef355c53a08190a8a92e355a7ce115 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f627b403d0819083ef8ed23f802e35 |
completed | May 2, 2026, 4:35 p.m. |
| PD | Predicate disambiguation | batch_69f620e4b1c88190a17940251abc68fd |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:29 a.m.