Triple
T17262118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diskhaler |
E419032
|
entity |
| Predicate | usesDosageForm |
P23152
|
FINISHED |
| Object | blister disc |
—
|
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: blister disc | Statement: [Diskhaler, usesDosageForm, blister disc]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesDosageForm Context triple: [Diskhaler, usesDosageForm, blister disc]
-
A.
hasDosageForm
chosen
Indicates the specific physical form or presentation in which a drug or medicinal product is supplied or administered (e.g., tablet, injection, cream).
-
B.
dosageStyles
Indicates the various ways or formats in which a dosage (amount and schedule of administration) is specified or presented for a treatment or medication.
-
C.
typicalDosageStyles
Indicates the usual ways or patterns in which a dosage is administered or presented (e.g., standard amounts, frequencies, or formats).
-
D.
dosageStyle
Indicates the manner or pattern in which a dose of a substance (such as a medication) is administered or taken.
-
E.
approvedDrugForm
Indicates that a particular pharmaceutical form (e.g., tablet, injection) is an officially approved formulation of a given drug.
- 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_69d886d9ab108190b70edd8d17aa1204 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e717a348190ae6835fb08f38125 |
completed | April 19, 2026, 1:22 a.m. |
| PD | Predicate disambiguation | batch_69e3832a284481908a8a3da7ac91de5a |
completed | April 18, 2026, 1:12 p.m. |
Created at: April 10, 2026, 5:39 a.m.