Triple
T12073896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AOC Lentille verte du Puy |
E287494
|
entity |
| Predicate | labelingRequirement |
P63670
|
FINISHED |
| Object | must be grown within delimited area |
—
|
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: must be grown within delimited area | Statement: [AOC Lentille verte du Puy, labelingRequirement, must be grown within delimited area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: labelingRequirement Context triple: [AOC Lentille verte du Puy, labelingRequirement, must be grown within delimited area]
-
A.
packagingRequirement
Indicates the specific conditions, standards, or constraints that must be met in how something is packaged.
-
B.
labelingRule
chosen
Indicates that a specified rule or criterion is used to assign a particular label or category to an entity.
-
C.
usedInLabeling
Indicates that something is employed or applied as part of a labeling process or activity.
-
D.
requiredToProvide
Indicates that one entity has an obligation or duty to supply or furnish something to another entity.
-
E.
homologationRequirement
Indicates that an entity is subject to a formal approval or certification process that must be completed before it can be legally accepted, used, or marketed.
- 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_69d6ab4846e081908ee7bbd66a6d3459 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9100b4ca8819084845ca4c13e34ce |
completed | April 10, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69d902bda47c8190b94860b31df4a98c |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:48 p.m.