Triple
T35731604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toraja coffee |
E1032764
|
entity |
| Predicate | roastPreference |
P117501
|
FINISHED |
| Object | medium 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 roast | Statement: [Toraja coffee, roastPreference, medium roast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roastPreference Context triple: [Toraja coffee, roastPreference, medium roast]
-
A.
roastProfile
chosen
Indicates the specific roasting characteristics or level applied to an item (typically coffee), defining how it was roasted.
-
B.
hasRoastType
Indicates that one entity is characterized by or associated with a specific roast type of another entity.
-
C.
typicalRoastUse
Indicates that something is commonly or characteristically used for roasting.
-
D.
hasRoastMaster
Indicates that something is associated with or assigned a specific roast master responsible for overseeing its roasting process.
-
E.
preparationPreference
Indicates how an entity prefers something to be prepared, processed, or made ready (e.g., style, method, or conditions of preparation).
- 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_69f76e10e59081908d81ad9ce22f40b6 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a34f8ee08190a040304635539a8f |
completed | May 3, 2026, 7:34 p.m. |
| PD | Predicate disambiguation | batch_69f7a06f125c8190843af194f042a465 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:05 p.m.