Triple
T22462136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ricard |
E555255
|
entity |
| Predicate | typicalServingRatio |
P112061
|
FINISHED |
| Object | 1 part Ricard to 5 parts water |
—
|
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: 1 part Ricard to 5 parts water | Statement: [Ricard, typicalServingRatio, 1 part Ricard to 5 parts water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalServingRatio Context triple: [Ricard, typicalServingRatio, 1 part Ricard to 5 parts water]
-
A.
typicalIngredientRatio
chosen
Indicates the usual proportional relationship between different ingredients used together in a preparation or mixture.
-
B.
commonServingSize
Indicates that two or more food items share the same standard or typical serving size used for comparison or labeling.
-
C.
typicalPortionPerBowl
Indicates the usual or standard quantity served in a single bowl for a given item or context.
-
D.
marketedAsServing
Indicates that something is promoted or advertised as providing service to a particular audience, purpose, or function.
-
E.
isTypicallyServedFor
Indicates that one item is most commonly or customarily served as a meal or course for the other (e.g., a dish typically served for breakfast, lunch, or dinner).
- 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_69f15b80983081908084947b2e31c9d4 |
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.