Triple
T31253783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Da Hong Pao |
E796902
|
entity |
| Predicate | typicalRoastLevel |
P172775
|
FINISHED |
| Object | medium to heavy roast |
—
|
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: medium to heavy roast | Statement: [Da Hong Pao, typicalRoastLevel, medium to heavy roast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalRoastLevel Context triple: [Da Hong Pao, typicalRoastLevel, medium to heavy roast]
-
A.
typicalRoastUse
Indicates that something is commonly or characteristically used for roasting.
-
B.
hasRoastType
chosen
Indicates that one entity is characterized by or associated with a specific roast type of another entity.
-
C.
typicalSweetnessLevel
Indicates the usual or characteristic degree of sweetness associated with something.
-
D.
typicalEspressoType
Indicates that one entity is a standard or commonly recognized type or style of espresso in relation to another entity.
-
E.
featuresRoastee
Indicates that one entity presents or highlights another entity as the subject being roasted (e.g., in a comedic or critical context).
- 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_69f224dc84d0819081f1cb6f9127e6b1 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e5174c8190a0bdde7e381b7624 |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 29, 2026, 9:12 p.m.