Triple
T10959813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arabica |
E258939
|
entity |
| Predicate | bitternessComparedToRobusta |
P38317
|
FINISHED |
| Object | less bitter |
—
|
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: less bitter | Statement: [Arabica, bitternessComparedToRobusta, less bitter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bitternessComparedToRobusta Context triple: [Arabica, bitternessComparedToRobusta, less bitter]
-
A.
hasBitternessLevel
chosen
Indicates that an entity is associated with a specific degree or intensity of bitterness.
-
B.
coffeeVariety
Indicates a relationship where a specific type or variety of coffee is associated with a coffee-related entity (such as a product, beverage, or plant).
-
C.
tanninLevel
Indicates the degree or intensity of tannins present in or associated with something, typically a beverage like wine or tea.
-
D.
coffeeDesignationType
Indicates the specific classification or type designation assigned to a coffee (e.g., by quality, origin, or regulatory category).
-
E.
coffeeDesignation
Indicates that one entity is designated or classified as a particular type, role, or category of coffee in relation to another entity.
- 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_69d6aa88500c819097d7032ca578e74f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d77127b10481908ad1efafb2a338d1 |
completed | April 9, 2026, 9:28 a.m. |
| PD | Predicate disambiguation | batch_69d72e874f48819096ffa878f90c7d5b |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:23 p.m.