Triple
T29915909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cantonese ginger milk curd |
E759794
|
entity |
| Predicate | hasTypicalSweetener |
P65313
|
FINISHED |
| Object | white sugar |
—
|
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: white sugar | Statement: [Cantonese ginger milk curd, hasTypicalSweetener, white sugar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalSweetener Context triple: [Cantonese ginger milk curd, hasTypicalSweetener, white sugar]
-
A.
containsSweeteners
Indicates that something includes one or more sweetening substances as part of its composition or contents.
-
B.
sweetenerType
chosen
Indicates the specific kind or category of sweetener associated with or used in relation to an entity.
-
C.
containsArtificialSweeteners
Indicates that something includes one or more artificial sweetening substances as part of its composition.
-
D.
containsAddedSugar
Indicates that the subject includes sugar that has been added during processing or preparation, rather than only naturally occurring sugars.
-
E.
hasSugarContent
Indicates that one entity possesses or contains a specified amount or level of sugar.
- 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_69f2246189fc8190996b63ee1f9a2374 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fdd07a34c08190982b8c61c2775cf6 |
completed | May 8, 2026, noon |
| PD | Predicate disambiguation | batch_69fdbd25c7908190b72fca8de7ce503f |
completed | May 8, 2026, 10:38 a.m. |
Created at: April 29, 2026, 6:12 p.m.