Triple
T1172216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aduhelm |
E24938
|
entity |
| Predicate | drugClass |
P24605
|
FINISHED |
| Object | anti-amyloid monoclonal antibody |
—
|
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: anti-amyloid monoclonal antibody | Statement: [Aduhelm, drugClass, anti-amyloid monoclonal antibody]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: drugClass Context triple: [Aduhelm, drugClass, anti-amyloid monoclonal antibody]
-
A.
protectedDrugClassesInclude
Indicates that the specified set of protected drug classes includes the referenced drug class or classes.
-
B.
typeOfRemedy
Indicates that one entity is a specific kind or category of remedy in relation to another entity.
-
C.
typicalDosageCategories
Indicates the standard dosage ranges or categories typically associated with a given treatment, substance, or medication.
-
D.
hasDosageForm
Indicates the specific physical form or presentation in which a drug or medicinal product is supplied or administered (e.g., tablet, injection, cream).
-
E.
isProdrugOf
Indicates that one substance is a precursor form that is metabolized in the body to produce the active form of another substance.
- F. None of above. chosen
Provenance (4 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_69a4bceb3f188190b8b767380fe5986f |
completed | March 1, 2026, 10:25 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5656948190b0b1d5446ad06005 |
completed | March 1, 2026, 10:19 p.m. |
| PDg | Predicate description generation | batch_69a4bbd7ff1881908c943ecdfea59e81 |
completed | March 1, 2026, 10:21 p.m. |
Created at: March 1, 2026, 7:45 p.m.