Triple
T28872480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FHIR DocumentReference |
E732174
|
entity |
| Predicate | supportsSearchParameter |
P74197
|
FINISHED |
| Object | patient |
—
|
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: patient | Statement: [FHIR DocumentReference, supportsSearchParameter, patient]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsSearchParameter Context triple: [FHIR DocumentReference, supportsSearchParameter, patient]
-
A.
hasSearchField
Indicates that an entity includes or is associated with a search input field that can be used to query or filter information.
-
B.
supportsPartialMatch
Indicates that the relationship or operation allows matching based on a subset or portion of the target criteria rather than requiring a complete or exact match.
-
C.
supportsPositionalParameters
Indicates that one entity allows or enables the use of positional parameters when invoking an operation or function.
-
D.
searchesOver
Indicates that one entity actively looks through, queries, or examines another entity or set of entities to find information or items.
-
E.
isSearchable
chosen
Indicates that the referenced entity can be discovered or retrieved through a search operation or query.
- 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_6a021706e21c81909b83e2b4d9c4130c |
completed | May 11, 2026, 5:51 p.m. |
| PD | Predicate disambiguation | batch_6a0216861214819097d2177755bc19d7 |
completed | May 11, 2026, 5:48 p.m. |
Created at: April 28, 2026, 7:34 a.m.