Triple
T22441867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sichuan peppercorn |
E554770
|
entity |
| Predicate | sensoryEffect |
P35696
|
FINISHED |
| Object | mouth-numbing |
—
|
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: mouth-numbing | Statement: [Sichuan peppercorn, sensoryEffect, mouth-numbing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sensoryEffect Context triple: [Sichuan peppercorn, sensoryEffect, mouth-numbing]
-
A.
providesSensoryEffects
chosen
Indicates that one entity causes or contributes to sensory experiences or perceptions in another entity.
-
B.
sensoryModality
Indicates the type of sensory channel (e.g., visual, auditory, tactile) through which an experience, perception, or information is received or processed.
-
C.
hasSensation
Indicates that an entity experiences or is subject to a particular sensory or perceptual feeling.
-
D.
sensoryCommunication
Indicates a relationship where one entity conveys or exchanges information with another through sensory signals or perception-based means.
-
E.
senses
Indicates that an entity perceives or detects another entity or stimulus through one of its senses.
- 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_69e11e5010e48190ae1e9c9db9697637 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ae2f7608190b1c1e8bd12ca2162 |
completed | April 29, 2026, 1:12 a.m. |
| PD | Predicate disambiguation | batch_69e898a327948190beee5e168006a0a7 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:47 p.m.