Triple
T32394112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johannisberg |
E827754
|
entity |
| Predicate | traditionalVarietyShare |
P196249
|
FINISHED |
| Object | predominantly Riesling |
—
|
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: predominantly Riesling | Statement: [Johannisberg, traditionalVarietyShare, predominantly Riesling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalVarietyShare Context triple: [Johannisberg, traditionalVarietyShare, predominantly Riesling]
-
A.
traditionalVariety
chosen
Indicates that one entity is a traditional or long-established variety, type, or form of another entity.
-
B.
typicalVariety
Indicates that one entity is a representative or characteristic example of the variety or type defined by another entity.
-
C.
varietyOf
Indicates that one entity is a specific type, kind, or variant of another, more general entity.
-
D.
hasNonStandardizedVarieties
Indicates that an entity possesses forms or variants that are not governed by a uniform or officially established standard.
-
E.
hasVarietyOf
Indicates that an entity possesses or offers multiple different types, forms, or versions of something.
- 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_69f349184e7481909c6c54428cb9cf12 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69feabcda59481908f2bc13b46fcced1 |
completed | May 9, 2026, 3:36 a.m. |
| PD | Predicate disambiguation | batch_69feaabd63f88190b30dcf6dd2ea39d1 |
completed | May 9, 2026, 3:32 a.m. |
Created at: May 1, 2026, 12:52 a.m.