Triple
T11782391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michigan AVA system |
E280181
|
entity |
| Predicate | productTypeCovered |
P44687
|
FINISHED |
| Object | grape wine |
—
|
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: grape wine | Statement: [Michigan AVA system, productTypeCovered, grape wine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: productTypeCovered Context triple: [Michigan AVA system, productTypeCovered, grape wine]
-
A.
providesCoverage
Indicates that one entity supplies protection, insurance, or service coverage to another entity or for a specified risk or scope.
-
B.
typicallyCovers
Indicates that one entity is the kind of thing that usually or normally includes, addresses, or encompasses another entity.
-
C.
appliesToProductType
chosen
Indicates that something (such as a rule, offer, or condition) is relevant or applicable specifically to a certain type or category of product.
-
D.
typeOfCoverage
Indicates the specific kind or category of coverage that applies in a given context (such as insurance, service, or protection).
-
E.
hasCoverType
Indicates that one entity possesses or is associated with a specific type or category of cover.
- 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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a8c2e8b08190a31b1e284fca2aee |
completed | April 10, 2026, 7:37 a.m. |
| PD | Predicate disambiguation | batch_69d8a242cd8c819086ed6c5f292dc8cb |
completed | April 10, 2026, 7:09 a.m. |
Created at: April 8, 2026, 9:42 p.m.