Triple
T20301198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Farxiga |
E505482
|
entity |
| Predicate | doesNotTreat |
P139584
|
FINISHED |
| Object | type 1 diabetes mellitus |
—
|
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: type 1 diabetes mellitus | Statement: [Farxiga, doesNotTreat, type 1 diabetes mellitus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: doesNotTreat Context triple: [Farxiga, doesNotTreat, type 1 diabetes mellitus]
-
A.
doesNot
Indicates that a specified entity lacks, refrains from, or fails to perform a particular action or exhibit a particular property in relation to another entity or context.
-
B.
doesNotUsuallyHandle
Indicates that an entity is generally not responsible for or typically involved in performing a particular task, role, or type of item, even if it might do so in rare or exceptional cases.
-
C.
doesNotConsider
Indicates that one entity fails or chooses not to take another entity or factor into account when forming judgments, decisions, or actions.
-
D.
doesNotUse
Indicates that one entity intentionally refrains from employing, utilizing, or relying on another entity, method, or resource.
-
E.
doesNotAbolish
Indicates that one entity, action, or law does not eliminate, revoke, or put an end to another.
- 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_69e0b4b8ab648190906e18538c250148 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6770c700c81909da247cef0d0f1eb |
completed | April 20, 2026, 6:57 p.m. |
| PD | Predicate disambiguation | batch_69e55b21b09081909e46691b6f45a07f |
completed | April 19, 2026, 10:45 p.m. |
| PDg | Predicate description generation | batch_69e56702ad04819099c1c08f28d16809 |
completed | April 19, 2026, 11:36 p.m. |
Created at: April 16, 2026, 11:17 a.m.