Triple
T28871981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DICOM Frame of Reference |
E732165
|
entity |
| Predicate | hasDICOMTag |
P192429
|
FINISHED |
| Object | (0020,0052) |
—
|
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: (0020,0052) | Statement: [DICOM Frame of Reference, hasDICOMTag, (0020,0052)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDICOMTag Context triple: [DICOM Frame of Reference, hasDICOMTag, (0020,0052)]
-
A.
hasIETFTag
Indicates that an entity is associated with a specific IETF-defined tag or identifier, as standardized by the Internet Engineering Task Force.
-
B.
hasImagingType
Indicates the specific imaging modality or technique associated with or used in a given imaging procedure or result.
-
C.
hasTaxonomyTag
Indicates that an entity is associated with a specific taxonomy tag used for classification or categorization.
-
D.
hasTaggingSystem
Indicates that an entity is associated with or supports a system for assigning and managing tags or labels.
-
E.
hasTagLength
Indicates that an entity is associated with a tag whose length (typically in characters) has a specified value or satisfies a given constraint.
- F. None of above. chosen
Provenance (4 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_69fd0b92f42881908cd77e3f058adcc2 |
completed | May 7, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fd0a3d68d4819094d92040f7c48d7c |
completed | May 7, 2026, 9:55 p.m. |
| PDg | Predicate description generation | batch_69fd0b92150881909b1166fe6d09aa19 |
completed | May 7, 2026, 10 p.m. |
Created at: April 28, 2026, 7:33 a.m.