Triple
T16085356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kellerbier |
E390214
|
entity |
| Predicate | historicalServingVessel |
P22942
|
FINISHED |
| Object | wooden cask |
—
|
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: wooden cask | Statement: [Kellerbier, historicalServingVessel, wooden cask]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalServingVessel Context triple: [Kellerbier, historicalServingVessel, wooden cask]
-
A.
servingVessel
Indicates that one entity functions as the container or vessel used to serve another entity (such as food or drink).
-
B.
traditionalVessel
chosen
Indicates that one entity is a vessel or container that follows traditional, customary, or historically established forms, designs, or uses in relation to another entity.
-
C.
servesVessels
Indicates that one entity provides or supplies vessels (such as containers, ships, or similar items) for the use or benefit of another entity.
-
D.
tableware
Indicates that an entity is a piece of tableware (such as dishes, utensils, or related items) used in serving or consuming food and drink.
-
E.
possibleFermentationVessel
Indicates that something can serve as a suitable container or environment in which fermentation may take place.
- 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_69d87f198bc48190a8b7e53ca15b7ead |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e1ff63edb0819092cbb671967bbdcd |
completed | April 17, 2026, 9:37 a.m. |
| PD | Predicate disambiguation | batch_69e1827ad7c88190b867da511cbfb7fa |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 4:59 a.m.