Triple
T22871398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | branaplam |
E567204
|
entity |
| Predicate | administrationForm |
P39634
|
FINISHED |
| Object | oral solution |
—
|
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: oral solution | Statement: [branaplam, administrationForm, oral solution]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: administrationForm Context triple: [branaplam, administrationForm, oral solution]
-
A.
adminChange
Indicates that an administrative user performs or authorizes a modification to a system, resource, or configuration.
-
B.
administrationStep
Indicates a specific phase or stage within a broader administrative or management process.
-
C.
coversAdministration
Indicates that one entity is responsible for managing, overseeing, or handling the administrative aspects of another entity or activity.
-
D.
administersFrom
Indicates that an action, service, or process is carried out or managed starting from a particular source, location, or authority.
-
E.
administrationRoute
chosen
Indicates the method or pathway by which a substance or treatment is delivered to a subject or system.
- 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_69e24589d8348190b96422d13a678bc1 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17f05c688819097ba3d24ea8e52f5 |
completed | April 29, 2026, 3:46 a.m. |
| PD | Predicate disambiguation | batch_69eed2d8c0608190afef4c4e530c0e2c |
completed | April 27, 2026, 3:07 a.m. |
Created at: April 17, 2026, 3:38 p.m.