Triple
T20786418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geotrichum candidum |
E511648
|
entity |
| Predicate | odorImpact |
P6479
|
FINISHED |
| Object | contributes to mushroom-like and buttery notes in cheese 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: contributes to mushroom-like and buttery notes in cheese aroma | Statement: [Geotrichum candidum, odorImpact, contributes to mushroom-like and buttery notes in cheese aroma]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: odorImpact Context triple: [Geotrichum candidum, odorImpact, contributes to mushroom-like and buttery notes in cheese aroma]
-
A.
odor
chosen
Indicates that one entity emits, possesses, or is characterized by a particular smell detectable by another entity.
-
B.
hasEnvironmentalImpactOn
Indicates that one entity affects or alters the environmental conditions, quality, or ecological state of another entity.
-
C.
hostImpact
Indicates that one entity causes an effect, influence, or change on another entity that acts as its host.
-
D.
odorizedWith
Indicates that one entity has been treated or infused with another substance in order to give it a detectable odor.
-
E.
smokeImpact
Indicates the effect or influence that smoke has on a target entity or condition.
- 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_69e0b4cb83948190bd57bec21d78ed53 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c28c0d0c8190aa48e6fdfdaab750 |
completed | April 21, 2026, 12:19 a.m. |
| PD | Predicate disambiguation | batch_69e5c0550ec481908a0877fb2409d983 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:38 p.m.