Triple
T29915920
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cantonese ginger milk curd |
E759794
|
entity |
| Predicate | isUsuallyEaten |
P148210
|
FINISHED |
| Object | with a spoon |
—
|
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: with a spoon | Statement: [Cantonese ginger milk curd, isUsuallyEaten, with a spoon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isUsuallyEaten Context triple: [Cantonese ginger milk curd, isUsuallyEaten, with a spoon]
-
A.
isOftenEaten
Indicates that the subject is frequently consumed as food by some agent or group.
-
B.
isEatenIn
Indicates that one entity (typically food) is consumed within the context, location, or occasion specified by another entity.
-
C.
isTypicallyEatenWith
chosen
Indicates that one item is commonly consumed together with another as part of the same eating occasion or dish.
-
D.
isEatenFor
Indicates that one entity is consumed as food for the benefit, nourishment, or use of another entity.
-
E.
isUsuallyCookedIn
Indicates that something is most commonly or typically prepared or cooked within a particular container, appliance, or environment.
- 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_69f6778f9c248190b61955450e10fd02 |
completed | May 2, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69f66ec8298c8190b41fe9d182c05676 |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 29, 2026, 6:12 p.m.