Triple
T33205922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | carbamazepine |
E850013
|
entity |
| Predicate | mayTreat |
P85563
|
FINISHED |
| Object | schizoaffective disorder |
—
|
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: schizoaffective disorder | Statement: [carbamazepine, mayTreat, schizoaffective disorder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayTreat Context triple: [carbamazepine, mayTreat, schizoaffective disorder]
-
A.
mayPrescribe
Indicates that one entity is authorized or permitted to prescribe something (typically a medication or treatment) to another entity.
-
B.
mayTake
Indicates that an entity is permitted or allowed to take, enroll in, or participate in another entity (such as a course, resource, or opportunity).
-
C.
mayAlsoAdmit
Indicates that an entity has the option or authority to additionally allow or accept another entity, beyond any primary or default admission.
-
D.
mayAdmit
Indicates that one entity has the permission or authority to allow another entity to enter, join, or be accepted into something.
-
E.
treatsConditionType
chosen
Indicates that one entity (typically a treatment, procedure, or intervention) is used to address, manage, or cure a particular type or category of medical 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_69f3495fb92c819083ce65d0ddee7a76 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6dd3cc0648190a275812d6711275a |
completed | May 3, 2026, 5:29 a.m. |
| PD | Predicate disambiguation | batch_69f6d82eaee081908f06a71546315aea |
completed | May 3, 2026, 5:07 a.m. |
Created at: May 1, 2026, 1:30 a.m.