Triple
T1169438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spinraza |
E24879
|
entity |
| Predicate | isFirstDrugApprovedFor |
P24561
|
FINISHED |
| Object | spinal muscular atrophy |
—
|
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: spinal muscular atrophy | Statement: [Spinraza, isFirstDrugApprovedFor, spinal muscular atrophy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFirstDrugApprovedFor Context triple: [Spinraza, isFirstDrugApprovedFor, spinal muscular atrophy]
-
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.
firstUsedOn
Indicates the date, time, or context in which something was initially applied, activated, or put into use on a particular object or entity.
-
C.
hasInitialDose
Indicates that an entity has received or is assigned a first or starting dose of a treatment, medication, or substance.
-
D.
formulatedInYear
Indicates the specific calendar year in which something was originally created, devised, or formally established.
-
E.
firstUsedFor
Indicates that one entity was the earliest or original thing for which another entity was used or applied.
- F. None of above. chosen
Provenance (4 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_69a494082a7c819095004f423f294a64 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bce821b481908bc278a3fa7973f4 |
completed | March 1, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5656948190b0b1d5446ad06005 |
completed | March 1, 2026, 10:19 p.m. |
| PDg | Predicate description generation | batch_69a4bbd7ff1881908c943ecdfea59e81 |
completed | March 1, 2026, 10:21 p.m. |
Created at: March 1, 2026, 7:45 p.m.