Triple
T34654463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rènnas del Castèl |
E889933
|
entity |
| Predicate | regionLanguageHeritage |
P11341
|
FINISHED |
| Object | Occitan culture |
—
|
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: Occitan culture | Statement: [Rènnas del Castèl, regionLanguageHeritage, Occitan culture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionLanguageHeritage Context triple: [Rènnas del Castèl, regionLanguageHeritage, Occitan culture]
-
A.
heritageLanguage
Indicates that one entity is the ancestral or culturally inherited language associated with another entity.
-
B.
regionLanguage
Indicates that a particular language is used or officially recognized within a specific geographic region.
-
C.
isCulturalLanguageOf
chosen
Indicates that a language serves as a primary medium of cultural expression, identity, and heritage for a particular group, community, or region.
-
D.
hasLinguisticHeritage
Indicates that one entity possesses or is associated with the linguistic background, tradition, or ancestry of another entity.
-
E.
languageOfSurroundingCulture
Indicates that one entity is the language predominantly used or characteristic of the surrounding culture associated with another 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_69f349d906bc8190b2efd9eff237d94b |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff8cecbf048190860b9f72b8753f5c |
completed | May 9, 2026, 7:37 p.m. |
| PD | Predicate disambiguation | batch_69ff8c4c39dc8190b5bf35adc1bae7c6 |
completed | May 9, 2026, 7:34 p.m. |
Created at: May 1, 2026, 2:04 a.m.