Triple
T21057657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ocrelizumab |
E518760
|
entity |
| Predicate | effectOnImmuneSystem |
P40373
|
FINISHED |
| Object | selective depletion of CD20-expressing B cells |
—
|
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: selective depletion of CD20-expressing B cells | Statement: [ocrelizumab, effectOnImmuneSystem, selective depletion of CD20-expressing B cells]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectOnImmuneSystem Context triple: [ocrelizumab, effectOnImmuneSystem, selective depletion of CD20-expressing B cells]
-
A.
effectOnSystem
chosen
Indicates the influence, change, or impact that one entity, action, or condition has on the state or behavior of a system.
-
B.
immunityType
Indicates the specific kind or category of immunity that applies in a given context (e.g., legal, diplomatic, medical).
-
C.
immunity
Indicates that an entity is protected against or not affected by a particular agent, condition, or influence.
-
D.
healthEffect
Indicates the impact or consequence that one entity has on the health or well-being of another.
-
E.
effectOnUser
Indicates how an action, event, or condition influences or impacts a user.
- 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_69e0b5053ac48190921529544959e906 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fd81434c8190aedfddf937f82322 |
completed | April 21, 2026, 4:30 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf9d71881908cd85dfc37db93ca |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:37 p.m.