Triple
T5981344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EMERGE (Study 302) |
E133123
|
entity |
| Predicate | intervention |
P7702
|
FINISHED |
| Object | intravenous aducanumab |
—
|
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: intravenous aducanumab | Statement: [EMERGE (Study 302), intervention, intravenous aducanumab]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intervention Context triple: [EMERGE (Study 302), intervention, intravenous aducanumab]
-
A.
interventionType
Indicates the specific kind or category of action, treatment, or measure applied in an intervention.
-
B.
usesIntervention
chosen
Indicates that one entity applies, employs, or relies on a specific intervention (such as a treatment, method, or strategy) in relation to another entity or context.
-
C.
intervenedIn
Indicates that an entity took action to alter, influence, or interrupt the course of an event, process, or interaction involving other entities.
-
D.
targetOfIntervention
Indicates that an entity is the object or focus upon which an intervention, treatment, or action is directed.
-
E.
intervenesWhen
Indicates that one entity takes action to interrupt, mediate, or alter the course of another entity’s ongoing situation or process when certain conditions arise.
- 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_69c0086f45e8819098f73dd16d45ec9d |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04a6921b081908a6f6323d5c7a062 |
completed | March 22, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69c049de98648190962b14fd341c93da |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:04 p.m.