Triple
T28034026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spätburgunder |
E708351
|
entity |
| Predicate | canBeBlendedWith |
P38059
|
FINISHED |
| Object | other red grape varieties |
—
|
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: other red grape varieties | Statement: [Spätburgunder, canBeBlendedWith, other red grape varieties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBeBlendedWith Context triple: [Spätburgunder, canBeBlendedWith, other red grape varieties]
-
A.
hasBlendOf
Indicates that something is composed of or contains a mixture of multiple specified components or elements.
-
B.
isBlended
Indicates that one entity has been mixed or combined thoroughly with another (or others) to form a uniform whole.
-
C.
mixesWith
chosen
Indicates that one entity is combined or blended together with another entity to form a mixture.
-
D.
usedInBlends
Indicates that something serves as an ingredient or component within one or more mixtures, combinations, or blends.
-
E.
hasBlendOfCharacter
Indicates that something exhibits a combination or mixture of multiple character traits or qualities.
- 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_69ef9b6bdd9c8190bb3a574a03774ad1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f7bbf906d8819099020e548dd56bc9 |
completed | May 3, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a2dcf88190a7c9e109e41267be |
completed | May 3, 2026, 9:09 p.m. |
Created at: April 27, 2026, 8:19 p.m.