Triple
T23892096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hengshui Laobaigan liquor |
E600795
|
entity |
| Predicate | hasAromaType |
P10884
|
FINISHED |
| Object | strong aroma |
—
|
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: strong aroma | Statement: [Hengshui Laobaigan liquor, hasAromaType, strong aroma]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAromaType Context triple: [Hengshui Laobaigan liquor, hasAromaType, strong aroma]
-
A.
characteristicAroma
Indicates that one entity has a distinctive smell or scent that characterizes or is typically associated with another entity.
-
B.
aromaticOilsPresent
Indicates that aromatic oils are present in or associated with the specified entity or context.
-
C.
hasFragrance
Indicates that one entity possesses or emits a particular scent or aroma associated with another entity.
-
D.
olfactoryFamily
chosen
Indicates a relationship where one entity belongs to, or is categorized within, a particular olfactory family or scent classification defined by the other entity.
-
E.
secondaryAroma
Indicates that an entity has a secondary or supporting aroma characteristic in addition to its primary scent.
- 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_69e295341ac0819080647f2908af793c |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cd044708819091102ecc160e1961 |
completed | April 29, 2026, 9:19 a.m. |
| PD | Predicate disambiguation | batch_69f1614e24b48190a1c8fb5b7c75ee0f |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:25 p.m.