Triple
T23106616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yangzhou fried rice |
E576185
|
entity |
| Predicate | typicalRiceType |
P50956
|
FINISHED |
| Object | day-old cooked rice |
—
|
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: day-old cooked rice | Statement: [Yangzhou fried rice, typicalRiceType, day-old cooked rice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalRiceType Context triple: [Yangzhou fried rice, typicalRiceType, day-old cooked rice]
-
A.
riceType
chosen
Indicates the specific variety or classification of rice associated with an entity.
-
B.
noodleType
Indicates the specific kind or category of noodle associated with an entity.
-
C.
numberOfRiceStalks
Indicates the quantity or count of rice stalks associated with a given entity or context.
-
D.
comparisonWithAsianRice
Indicates a relationship in which something is compared or contrasted specifically with Asian rice in terms of some property or characteristic.
-
E.
CRSRiceBowlType
Indicates that there is a specific type or category relationship between a rice bowl and its classification.
- 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e0bb27c8190a17942d9b88bb158 |
completed | April 29, 2026, 4:50 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:58 p.m.