Triple
T32147304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | crème brûlée |
E821054
|
entity |
| Predicate | toppingPreparationMethod |
P173632
|
FINISHED |
| Object | sugar caramelized with a kitchen torch |
—
|
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: sugar caramelized with a kitchen torch | Statement: [crème brûlée, toppingPreparationMethod, sugar caramelized with a kitchen torch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: toppingPreparationMethod Context triple: [crème brûlée, toppingPreparationMethod, sugar caramelized with a kitchen torch]
-
A.
typeOfPreparation
Indicates the method or process by which something is prepared or made ready for use, consumption, or further action.
-
B.
isTypicallyGarnishedWith
Indicates that one item is commonly used as a garnish or decorative finishing element for another.
-
C.
commonPreparationMethod
Indicates that two or more items share the same typical way of being prepared or processed.
-
D.
typicalPreparation
Indicates the usual or standard way in which something is prepared or made.
-
E.
textureOfTopping
Indicates the specific surface quality or mouthfeel characteristic of a topping in relation to the item it is applied to.
- F. None of above. chosen
Provenance (4 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_69f3490520d081909b2f1271dab75faa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b9e567908190abe980a80db9a7af |
completed | May 3, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a970b0819090c6473844ffa8e3 |
completed | May 3, 2026, 2:32 a.m. |
| PDg | Predicate description generation | batch_69f6b49339048190b617a6749f648825 |
completed | May 3, 2026, 2:36 a.m. |
Created at: May 1, 2026, 12:31 a.m.