Triple
T24108461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aristada |
E597293
|
entity |
| Predicate | notApprovedFor |
P105890
|
FINISHED |
| Object | treatment of dementia-related psychosis |
—
|
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: treatment of dementia-related psychosis | Statement: [Aristada, notApprovedFor, treatment of dementia-related psychosis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notApprovedFor Context triple: [Aristada, notApprovedFor, treatment of dementia-related psychosis]
-
A.
isApprovedFor
Indicates that one entity has been officially authorized, accepted, or permitted for use, access, or association with another entity.
-
B.
disapprovedOf
Indicates that one entity holds a negative judgment or lack of approval toward another entity or that entity’s actions.
-
C.
nonEligibility
Indicates that an entity does not meet the required conditions or criteria to qualify for a specified status, benefit, or action.
-
D.
notSanctionedBy
chosen
Indicates that an action, entity, or event is explicitly not approved, authorized, or endorsed by the referenced authority or organization.
-
E.
notSufficientFor
Indicates that the presence or occurrence of one condition does not by itself guarantee or bring about the other condition.
- 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_69e288c60f9c8190af948d7354aedbeb |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1de19057c819096a8b3290d33e2f6 |
completed | April 29, 2026, 10:31 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:02 p.m.