Triple
T20223050
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grenache Gris |
E495306
|
entity |
| Predicate | synonymLanguage |
P76128
|
FINISHED |
| Object | Garnacha Roja – Spanish |
—
|
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: Garnacha Roja – Spanish | Statement: [Grenache Gris, synonymLanguage, Garnacha Roja – Spanish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: synonymLanguage Context triple: [Grenache Gris, synonymLanguage, Garnacha Roja – Spanish]
-
A.
languageEquivalent
Indicates that two linguistic expressions convey the same meaning or function across different languages or language varieties.
-
B.
languageOfWord
Indicates that a particular language is the one in which a given word is expressed or defined.
-
C.
equivalentEpithetLanguage
chosen
Indicates that two epithets are expressed in different languages but convey the same meaning or designation.
-
D.
hasLanguageFormOf
Indicates that one entity is a specific linguistic form, expression, or realization of the language used by another entity.
-
E.
linguisticallyRelatedTo
Indicates that two entities are connected through a linguistic relationship, such as sharing a common language, origin, structure, or other language-based association.
- 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_69da626cff80819097b530718a7c98b6 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66fd729548190942bcf842f03c4cd |
completed | April 20, 2026, 6:26 p.m. |
| PD | Predicate disambiguation | batch_69e55b18609481909ab28bc8750a642f |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:39 p.m.