Triple
T22460794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isaac Carasso |
E555223
|
entity |
| Predicate | usedIngredient |
P12771
|
FINISHED |
| Object | fermented milk |
—
|
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: fermented milk | Statement: [Isaac Carasso, usedIngredient, fermented milk]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedIngredient Context triple: [Isaac Carasso, usedIngredient, fermented milk]
-
A.
usesIngredient
chosen
Indicates that one entity employs or incorporates another entity as an ingredient in its composition or creation.
-
B.
ingredientType
Indicates that one entity is classified as a specific type or category of ingredient in relation to another.
-
C.
usesIngredientInfluenceFrom
Indicates that one entity incorporates or applies the influence, properties, or effects derived from a particular ingredient in its action or outcome.
-
D.
culinaryUse
Indicates that one entity is used in the preparation, flavoring, or serving of food or drink for another entity.
-
E.
usesRecipeOf
Indicates that one entity prepares or creates something by following the recipe or formula originally defined or used by another entity.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b7eb5688190bd5e41d4d8189668 |
completed | April 29, 2026, 1:14 a.m. |
| PD | Predicate disambiguation | batch_69e898ad961c819098fd1e46129bddcc |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:48 p.m.