Triple
T17495995
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blanquette Méthode Ancestrale |
E426060
|
entity |
| Predicate | sweetnessProfile |
P62205
|
FINISHED |
| Object | naturally sweet |
—
|
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: naturally sweet | Statement: [Blanquette Méthode Ancestrale, sweetnessProfile, naturally sweet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sweetnessProfile Context triple: [Blanquette Méthode Ancestrale, sweetnessProfile, naturally sweet]
-
A.
typicalSweetnessLevel
chosen
Indicates the usual or characteristic degree of sweetness associated with something.
-
B.
sweetnessOnset
Indicates the point in time or conditions under which sweetness first becomes perceptible in relation to something.
-
C.
sweetenerType
Indicates the specific kind or category of sweetener associated with or used in relation to an entity.
-
D.
sweetening
Indicates the action or process of making something taste sweeter, often by adding a sweet substance.
-
E.
sweetenerVariant
Indicates that one sweetening agent is a specific type, version, or alternative form of another sweetening agent.
- 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_69d889dccf7481909264a1844a2e9100 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4520e9c8c8190aa955766bc915d26 |
completed | April 19, 2026, 3:54 a.m. |
| PD | Predicate disambiguation | batch_69e3b4f5fbcc8190a6ea9639bf5650da |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:48 a.m.