Triple
T22517021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DayTime IPA |
E556674
|
entity |
| Predicate | caloriesPerServing |
P51659
|
FINISHED |
| Object | 98 calories (per 12 oz) |
—
|
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: 98 calories (per 12 oz) | Statement: [DayTime IPA, caloriesPerServing, 98 calories (per 12 oz)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: caloriesPerServing Context triple: [DayTime IPA, caloriesPerServing, 98 calories (per 12 oz)]
-
A.
hasCalories
chosen
Indicates that an entity contains a specified amount of caloric energy.
-
B.
commonServingSize
Indicates that two or more food items share the same standard or typical serving size used for comparison or labeling.
-
C.
calorieLevel
Indicates the relationship between an entity and the amount of calories it contains or provides, typically categorized by intensity or range (e.g., low, medium, high).
-
D.
marketedAsServing
Indicates that something is promoted or advertised as providing service to a particular audience, purpose, or function.
-
E.
carbohydratesPer12Ounces
Indicates the amount of carbohydrates contained in a 12-ounce serving of a given item.
- 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_69e11e5657e881909f16ca58352c50da |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15e2df59c81909c4ae2f20f1cbb32 |
completed | April 29, 2026, 1:26 a.m. |
| PD | Predicate disambiguation | batch_69ee625e3b408190a60c759fb0b28fe2 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 16, 2026, 8:50 p.m.