Triple
T19029619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roquefort-sur-Soulzon |
E465699
|
entity |
| Predicate | cheeseMaturationCondition |
P99652
|
FINISHED |
| Object | ventilated caves with fleurines |
—
|
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: ventilated caves with fleurines | Statement: [Roquefort-sur-Soulzon, cheeseMaturationCondition, ventilated caves with fleurines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cheeseMaturationCondition Context triple: [Roquefort-sur-Soulzon, cheeseMaturationCondition, ventilated caves with fleurines]
-
A.
cheeseRipeningStyle
chosen
Indicates the method or process by which a cheese is matured or aged to develop its flavor and texture.
-
B.
isMeltingCheese
Indicates that one entity is causing cheese to transition from a solid to a softened or liquid state through heating or similar means.
-
C.
cheeseMadeFrom
Indicates that one entity is produced or derived as cheese from another entity (typically a source ingredient such as milk).
-
D.
cheeseType
Indicates that one entity is a specific type or variety of cheese in relation to another entity.
-
E.
traditionalCheese
Indicates that something is recognized as a cheese made according to established, customary, or historically rooted methods or styles.
- 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_69d8dd0359648190bc2a9202c5cf29d2 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d73f98dc81909acbb366f00d2d54 |
completed | April 20, 2026, 7:35 a.m. |
| PD | Predicate disambiguation | batch_69e4a2fd80c081908237317a3a883e1c |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 12:02 p.m.