Triple
T21057610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ocrelizumab |
E518760
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | humanized monoclonal antibody |
C7047
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: humanized monoclonal antibody Context triple: [ocrelizumab, instanceOf, humanized monoclonal antibody]
-
A.
monoclonal antibody
chosen
A monoclonal antibody is a laboratory-produced molecule engineered to bind specifically to a single epitope on an antigen, enabling targeted detection or treatment of diseases.
-
B.
biologic medicinal product
A biologic medicinal product is a therapeutic substance derived from living organisms or their components, such as proteins, cells, or tissues, used to prevent, diagnose, or treat diseases.
-
C.
Bruton tyrosine kinase inhibitor
A Bruton tyrosine kinase inhibitor is a targeted small-molecule drug that blocks BTK signaling in B cells to disrupt pathways critical for their activation, proliferation, and survival, primarily used in the treatment of certain B-cell malignancies and autoimmune diseases.
-
D.
cluster of differentiation antigen
A cluster of differentiation antigen is a cell surface molecule used as a marker to identify and classify leukocyte subsets and other cell types, often serving functional roles in cell signaling and immune responses.
-
E.
antineoplastic immunomodulating agent
An antineoplastic immunomodulating agent is a drug that treats cancer by modifying or enhancing the body’s immune response to recognize and destroy malignant cells.
- F. None of above.
Provenance (1 batch)
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_69e0b5053ac48190921529544959e906 |
completed | April 16, 2026, 10:08 a.m. |
Created at: April 16, 2026, 2:37 p.m.