Triple
T22441833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sichuan peppercorn |
E554770
|
entity |
| Predicate | activeCompound |
P67837
|
FINISHED |
| Object | hydroxy-alpha-sanshool |
—
|
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: hydroxy-alpha-sanshool | Statement: [Sichuan peppercorn, activeCompound, hydroxy-alpha-sanshool]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: activeCompound Context triple: [Sichuan peppercorn, activeCompound, hydroxy-alpha-sanshool]
-
A.
isProdrugOf
Indicates that one substance is a precursor form that is metabolized in the body to produce the active form of another substance.
-
B.
primaryDrug
Indicates that one drug is identified as the main or most important medication in a given treatment, context, or combination relative to other associated drugs.
-
C.
commonCompound
Indicates that the two entities share at least one chemical compound in common.
-
D.
hasInactiveIngredient
Indicates that one entity contains another entity as a non-active (inactive) component or ingredient.
-
E.
chemicalComponent
chosen
Indicates that one entity is a constituent chemical part or ingredient 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_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.