Triple
T8757794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mountain Chill |
E208115
|
entity |
| Predicate | sensoryEffectClaim |
P35696
|
FINISHED |
| Object | cooling sensation |
—
|
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: cooling sensation | Statement: [Mountain Chill, sensoryEffectClaim, cooling sensation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sensoryEffectClaim Context triple: [Mountain Chill, sensoryEffectClaim, cooling sensation]
-
A.
providesSensoryEffects
chosen
Indicates that one entity causes or contributes to sensory experiences or perceptions in another entity.
-
B.
sensoryCommunication
Indicates a relationship where one entity conveys or exchanges information with another through sensory signals or perception-based means.
-
C.
senses
Indicates that an entity perceives or detects another entity or stimulus through one of its senses.
-
D.
sensingAction
Indicates an action in which an entity perceives, detects, or measures some property, signal, or condition of another entity or its environment.
-
E.
sensitivityFeature
Indicates a relationship where one entity functions as a sensitivity-related characteristic, parameter, or attribute of 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_69ca835cd6b08190bd7c63db92f53c86 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5ddc2d9c81908948aee2b956cce4 |
completed | March 31, 2026, 11:50 p.m. |
| PD | Predicate disambiguation | batch_69cc5c1884bc8190a46e8308db31f7ab |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:40 p.m.