Triple
T16211659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hirudo medicinalis |
E393479
|
entity |
| Predicate | approvedMedicalUse |
P40313
|
FINISHED |
| Object | adjunct therapy in plastic surgery |
—
|
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: adjunct therapy in plastic surgery | Statement: [Hirudo medicinalis, approvedMedicalUse, adjunct therapy in plastic surgery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approvedMedicalUse Context triple: [Hirudo medicinalis, approvedMedicalUse, adjunct therapy in plastic surgery]
-
A.
medicinalUse
chosen
Indicates that one entity is used as a treatment or remedy for a disease, condition, or health-related purpose affecting another entity.
-
B.
approvedDrugForm
Indicates that a particular pharmaceutical form (e.g., tablet, injection) is an officially approved formulation of a given drug.
-
C.
potentialTherapeuticUse
Indicates that something is being considered or investigated as a possible treatment or therapy for a condition or disease.
-
D.
approvedPractice
Indicates that a particular practice, method, or procedure has been formally reviewed and granted official approval for use or adoption.
-
E.
eligibleUses
Indicates the types of actions, purposes, or contexts in which something is permitted or qualified to be used.
- 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_69d87f1f5bd08190bd01cac0d5b9d2ef |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e227f1bef8819094e724f5cd0b86d5 |
completed | April 17, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_69e219e94a448190b73a4e6aa374eb4a |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:03 a.m.