Triple
T22692998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SUNFISH |
E561097
|
entity |
| Predicate | drugClassStudied |
P97062
|
FINISHED |
| Object | SMN2 splicing modifier |
—
|
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 splicing modifier | Statement: [SUNFISH, drugClassStudied, SMN2 splicing modifier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: drugClassStudied Context triple: [SUNFISH, drugClassStudied, SMN2 splicing modifier]
-
A.
drugClass
Indicates that one entity is classified as a particular pharmacological or therapeutic category of drugs in relation to another entity.
-
B.
hasPharmacologicClass
Indicates that a drug or medicinal product belongs to a specific pharmacologic class based on its mechanism of action or therapeutic effect.
-
C.
protectedDrugClassesInclude
Indicates that the specified set of protected drug classes includes the referenced drug class or classes.
-
D.
evaluatedDrug
chosen
Indicates that a particular drug has been assessed or tested, typically in the context of a study, experiment, or evaluation process.
-
E.
developedDrugFor
Indicates that one entity created or formulated a drug intended to treat or address a medical condition associated with 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_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.