Triple
T2371075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Activase |
E46090
|
entity |
| Predicate | majorAdverseEffect |
P24552
|
FINISHED |
| Object | intracranial hemorrhage |
—
|
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: intracranial hemorrhage | Statement: [Activase, majorAdverseEffect, intracranial hemorrhage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorAdverseEffect Context triple: [Activase, majorAdverseEffect, intracranial hemorrhage]
-
A.
commonAdverseReactions
Indicates that the related entities are linked through adverse reactions or side effects that frequently occur in association with one another.
-
B.
hasCommonAdverseEffect
Indicates that two or more entities share at least one adverse effect that occurs in response to them.
-
C.
hasSeriousSideEffect
chosen
Indicates that an entity (such as a treatment, drug, or intervention) causes or is associated with a significant or severe adverse effect on another entity (typically a patient or biological system).
-
D.
majorIssue
Indicates that something is a primary or most significant problem, concern, or obstacle in a given context.
-
E.
majorStatus
Indicates that an entity holds primary or most significant status relative to others in a given context.
- 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_69a88a145268819083e2736cb835c696 |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc771302481908540e31abb5aeeba |
completed | March 7, 2026, 6:36 a.m. |
| PD | Predicate disambiguation | batch_69abc59b88348190a2d6c08f69974117 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:56 p.m.