Triple
T1172245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aduhelm |
E24938
|
entity |
| Predicate | initialDoseRegimen |
P23153
|
FINISHED |
| Object | titration to 10 mg/kg |
—
|
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: titration to 10 mg/kg | Statement: [Aduhelm, initialDoseRegimen, titration to 10 mg/kg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialDoseRegimen Context triple: [Aduhelm, initialDoseRegimen, titration to 10 mg/kg]
-
A.
hasInitialDose
chosen
Indicates that an entity has received or is assigned a first or starting dose of a treatment, medication, or substance.
-
B.
hasMaintenanceDose
Indicates that an entity is associated with a specific ongoing dose used to maintain a desired therapeutic effect after initial treatment.
-
C.
typicalDosageCategories
Indicates the standard dosage ranges or categories typically associated with a given treatment, substance, or medication.
-
D.
commonRouteOfAdministration
Indicates that two or more substances share the same typical method or pathway by which they are administered to a subject.
-
E.
hasDosageForm
Indicates the specific physical form or presentation in which a drug or medicinal product is supplied or administered (e.g., tablet, injection, cream).
- 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_69a494082a7c819095004f423f294a64 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bcecab688190b21a926874cd98d1 |
completed | March 1, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5656948190b0b1d5446ad06005 |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.