Triple
T27280047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Juliusspital Würzburg |
E688304
|
entity |
| Predicate | hasCellar |
P45100
|
FINISHED |
| Object | historic barrel cellar |
—
|
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: historic barrel cellar | Statement: [Juliusspital Würzburg, hasCellar, historic barrel cellar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCellar Context triple: [Juliusspital Würzburg, hasCellar, historic barrel cellar]
-
A.
hasCellars
chosen
Indicates that one entity possesses or contains one or more cellars associated with it.
-
B.
hasCellarDoorSales
Indicates that an entity conducts sales directly from its cellar door, typically on-site at the production location.
-
C.
hasWinery
Indicates a relationship where a subject owns, operates, or is associated with a particular winery.
-
D.
hasUndergroundCellarsLength
Indicates that an entity possesses underground cellars whose length is specified or measured.
-
E.
hasWineInstitution
Indicates that an entity is associated with, managed by, or belongs to a specific wine-related institution (such as a winery, wine school, or wine organization).
- 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_69ef3558cf8881909595ef89daf6e14a |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f6a8df16a88190a23820e64a3b1f92 |
completed | May 3, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69f6a751d5e48190a77dcecbe7ef9f0b |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 27, 2026, 11:06 a.m.