Triple
T22692963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FIREFISH |
E561096
|
entity |
| Predicate | usesDrugMechanism |
P58407
|
FINISHED |
| Object | SMN2 pre-mRNA splicing modification by risdiplam |
—
|
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: SMN2 pre-mRNA splicing modification by risdiplam | Statement: [FIREFISH, usesDrugMechanism, SMN2 pre-mRNA splicing modification by risdiplam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesDrugMechanism Context triple: [FIREFISH, usesDrugMechanism, SMN2 pre-mRNA splicing modification by risdiplam]
-
A.
usesDrug
Indicates that an entity consumes, administers, or otherwise makes use of a specified drug.
-
B.
hasPharmacologicalEffect
chosen
Indicates that one entity produces a specific pharmacological effect or action on another entity.
-
C.
featuresDrug
Indicates that something (such as a product, treatment, or context) includes, involves, or prominently uses a particular drug.
-
D.
isProdrugOf
Indicates that one substance is a precursor form that is metabolized in the body to produce the active form of another substance.
-
E.
associatedWithDrug
Indicates that an entity has a relevant relationship or connection to a specific drug, such as use, exposure, or involvement in its context.
- 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_69e2454d71b48190a1f80af9f82b6fcf |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1789ba0148190891781d05ec64f3c |
completed | April 29, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69ee62b2259c819091ed1387a748b9f3 |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:13 p.m.