Triple
T3603628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Washington Island lavender fields |
E76315
|
entity |
| Predicate | smell |
P6479
|
FINISHED |
| Object | strong floral lavender scent |
—
|
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 floral lavender scent | Statement: [Washington Island lavender fields, smell, strong floral lavender scent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: smell Context triple: [Washington Island lavender fields, smell, strong floral lavender scent]
-
A.
senseOfSmell
Indicates that one entity has the ability to detect or perceive odors or scents through the sense of smell.
-
B.
odor
chosen
Indicates that one entity emits, possesses, or is characterized by a particular smell detectable by another entity.
-
C.
olfactoryFamily
Indicates a relationship where one entity belongs to, or is categorized within, a particular olfactory family or scent classification defined by the other entity.
-
D.
hasFragrance
Indicates that one entity possesses or emits a particular scent or aroma associated with another entity.
-
E.
sillage
Indicates the lingering trail or trace left behind by something (such as a scent, movement, or presence) as it moves through space.
- 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_69ad85d93dcc819094fba90cf70f4996 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc1df08a48190a4a4a20c8821b321 |
completed | March 8, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69adb83d8b1c8190b3bddbc5dc995a87 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:22 p.m.