Triple
T24108480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aristada |
E597293
|
entity |
| Predicate | injectionSite |
P8805
|
FINISHED |
| Object | deltoid muscle (for some doses) |
—
|
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: deltoid muscle (for some doses) | Statement: [Aristada, injectionSite, deltoid muscle (for some doses)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: injectionSite Context triple: [Aristada, injectionSite, deltoid muscle (for some doses)]
-
A.
injectionType
Indicates the specific method or form by which an injection is administered or delivered.
-
B.
nearSiteOf
Indicates that one entity is located in close physical proximity to the site or location associated with another entity.
-
C.
administeredIn
chosen
Indicates that an action, treatment, or process is carried out or applied within a specific location, context, or jurisdiction.
-
D.
woundLocation
Indicates the specific anatomical site on an entity’s body where a wound is present or occurred.
-
E.
involvedLocation
Indicates that an event, action, or relationship takes place in, or is significantly associated with, a particular location.
- 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_69e288c60f9c8190af948d7354aedbeb |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1de19057c819096a8b3290d33e2f6 |
completed | April 29, 2026, 10:31 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:02 p.m.