Triple
T4691832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pastéis de Belém pastry shop |
E104050
|
entity |
| Predicate | usesRecipe |
P44302
|
FINISHED |
| Object | secret custard tart recipe |
—
|
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: secret custard tart recipe | Statement: [Pastéis de Belém pastry shop, usesRecipe, secret custard tart recipe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesRecipe Context triple: [Pastéis de Belém pastry shop, usesRecipe, secret custard tart recipe]
-
A.
usesRecipeOf
chosen
Indicates that one entity prepares or creates something by following the recipe or formula originally defined or used by another entity.
-
B.
usesIngredient
Indicates that one entity employs or incorporates another entity as an ingredient in its composition or creation.
-
C.
usesCookingMethod
Indicates that one entity prepares or processes another entity by applying a specific cooking technique or method.
-
D.
culinaryUse
Indicates that one entity is used in the preparation, flavoring, or serving of food or drink for another entity.
-
E.
servesUse
Indicates that one entity is used by or functions to serve the purpose or needs of 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_69bd43df91f481908e9add1b617b60ef |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd66059bfc8190885d26d05dd38df1 |
completed | March 20, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69bd6219da948190bbbb50f08573ab4d |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:16 p.m.