Triple
T21057628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ocrelizumab |
E518760
|
entity |
| Predicate | maintenanceDose |
P23154
|
FINISHED |
| Object | 600 mg intravenous infusion every 6 months |
—
|
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: 600 mg intravenous infusion every 6 months | Statement: [ocrelizumab, maintenanceDose, 600 mg intravenous infusion every 6 months]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintenanceDose Context triple: [ocrelizumab, maintenanceDose, 600 mg intravenous infusion every 6 months]
-
A.
hasMaintenanceDose
chosen
Indicates that an entity is associated with a specific ongoing dose used to maintain a desired therapeutic effect after initial treatment.
-
B.
hasCommonStartingDose_mgPerDay
Indicates that two treatments share the same typical initial dosage, measured in milligrams per day.
-
C.
doseRegimen
Indicates the specific schedule, frequency, and amount with which a dose of a substance or medication is to be administered.
-
D.
dosageLevel
Indicates the specific amount or intensity of a substance or treatment administered in a given dose.
-
E.
hasDosingRegimen
Indicates that an entity is associated with a specific dosing regimen, defining how and when a dose is to be administered.
- 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.