Triple
T28871737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DICOM structured reports |
E732160
|
entity |
| Predicate | commonlyUsesCodingScheme |
P60418
|
FINISHED |
| Object | SNOMED CT |
—
|
NE NERFINISHED |
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: SNOMED CT | Statement: [DICOM structured reports, commonlyUsesCodingScheme, SNOMED CT]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonlyUsesCodingScheme Context triple: [DICOM structured reports, commonlyUsesCodingScheme, SNOMED CT]
-
A.
standardCodeSystem
Indicates that an entity uses or is associated with a recognized, authoritative coding or classification system as its reference standard.
-
B.
commonlyAssociatedCodec
Indicates that one item is typically linked or paired with a particular codec in common usage or practice.
-
C.
classificationUsedBy
chosen
Indicates that a particular classification system or scheme is employed or applied by a given entity.
-
D.
codeUsedBy
Indicates that a specific piece of code is utilized or depended upon by another entity (such as a system, application, or component).
-
E.
relatedCodeSet
Indicates that one code set is associated with or connected to another code set in a meaningful or defined way.
- 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_69f05b06807c81909b4bbd4c20403a2b |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69fcd867f36081908c88c55a6a1404c1 |
completed | May 7, 2026, 6:22 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f47b188190b4cf4b4c748d9d03 |
completed | May 7, 2026, 5:55 p.m. |
Created at: April 28, 2026, 7:33 a.m.