Triple
T415592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Champagne |
E9584
|
entity |
| Predicate | viticulturalPractice |
P4104
|
FINISHED |
| Object | hand harvesting required |
—
|
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: hand harvesting required | Statement: [Champagne, viticulturalPractice, hand harvesting required]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: viticulturalPractice Context triple: [Champagne, viticulturalPractice, hand harvesting required]
-
A.
viticulturalCharacteristic
Indicates a relationship where a specific trait, quality, or property is attributed to viticulture or grape-growing practices.
-
B.
viticultureHistory
Indicates the historical development, practices, and events related to grape cultivation and winemaking over time.
-
C.
agriculturalPractice
chosen
Indicates a relationship where an entity engages in, applies, or is associated with a specific method or technique of agriculture or farming.
-
D.
primaryGrapeVariety
Indicates that one entity is the main or predominant grape variety used in producing the other entity (typically a wine or wine-based product).
-
E.
crop
Indicates the action of cutting or trimming part of an object or image, typically to remove unwanted outer areas while keeping a selected region.
- 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_69a2e80111fc8190961d5b7c6154123f |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2eebde1d881908fb212bfba9d7c67 |
completed | Feb. 28, 2026, 1:33 p.m. |
| PD | Predicate disambiguation | batch_69a2edcff4688190809d83d112ff25a5 |
completed | Feb. 28, 2026, 1:29 p.m. |
Created at: Feb. 28, 2026, 1:09 p.m.