Triple
T24054529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pepsi Max Lemon |
E595757
|
entity |
| Predicate | hasPrimaryIngredientType |
P40800
|
FINISHED |
| Object | carbonated 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: carbonated water | Statement: [Pepsi Max Lemon, hasPrimaryIngredientType, carbonated water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryIngredientType Context triple: [Pepsi Max Lemon, hasPrimaryIngredientType, carbonated water]
-
A.
hasMainIngredient
Indicates that one entity is the primary or most significant ingredient used to make another entity.
-
B.
hasPrimaryCarbohydrate
Indicates that one entity has another entity as its main or principal carbohydrate component.
-
C.
ingredientType
chosen
Indicates that one entity is classified as a specific type or category of ingredient in relation to another.
-
D.
hasDishType
Indicates that an item (such as a food or menu entry) is classified as belonging to a particular type of dish (e.g., appetizer, main course, dessert).
-
E.
hasCuisineItem
Indicates that a particular cuisine includes, features, or is associated with a specific food 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_69e288c184b081909f1f1751fb8e299a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d9d551288190a2b3b6c8c4f3c1b5 |
completed | April 29, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69f1764b1d4c8190b12590c6339c31c1 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:21 p.m.