Triple
T12881713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mango Dragonfruit Refresher |
E308110
|
entity |
| Predicate | dietaryProfile |
P34157
|
FINISHED |
| Object | non-dairy by default |
—
|
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: non-dairy by default | Statement: [Mango Dragonfruit Refresher, dietaryProfile, non-dairy by default]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dietaryProfile Context triple: [Mango Dragonfruit Refresher, dietaryProfile, non-dairy by default]
-
A.
nutritionType
Indicates the specific category or kind of nutritional characteristic or value associated with an entity.
-
B.
calorieProfile
Indicates the relationship between an entity and the detailed breakdown of its caloric characteristics, such as total calories and their distribution.
-
C.
dietVersion
Indicates that one diet is a specific version, variant, or iteration of another diet.
-
D.
dietaryOptions
chosen
Indicates the types of diets or food-related preferences, restrictions, or choices that are applicable to or offered for an entity.
-
E.
nutritionComponent
Indicates that one entity is a nutritional constituent, ingredient, or component of another (typically a food, diet, or nutritional product).
- 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_69d7bdf69bc48190af6c2621f28ca351 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97c7f91d08190aac2f6419d3ba992 |
completed | April 10, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_69d96fa55b888190ab1612e93c41aec4 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:39 p.m.