Triple
T14576917
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manhattan (cocktail) |
E342075
|
entity |
| Predicate | bitternessSource |
P100847
|
FINISHED |
| Object | aromatic bitters |
—
|
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: aromatic bitters | Statement: [Manhattan (cocktail), bitternessSource, aromatic bitters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bitternessSource Context triple: [Manhattan (cocktail), bitternessSource, aromatic bitters]
-
A.
bitterantType
chosen
Indicates the specific kind or category of bitterant used or associated with an entity.
-
B.
hasBitternessLevel
Indicates that an entity is associated with a specific degree or intensity of bitterness.
-
C.
isEmbittered
Indicates that an entity harbors persistent bitterness or resentment, typically as a result of past experiences or perceived wrongs.
-
D.
tanninLevel
Indicates the degree or intensity of tannins present in or associated with something, typically a beverage like wine or tea.
-
E.
grapeSource
Indicates that one entity is the origin or provider of grapes used by 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_69d822dcc6248190bed689984bceb0e2 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb3f5ec448190b2ef887fdf7b633e |
completed | April 14, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69de656a953481909a4645b004c40de7 |
completed | April 14, 2026, 4:03 p.m. |
Created at: April 10, 2026, 1:24 a.m.