Triple
T6723138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NHS Dental Exemption Certificates |
E153443
|
entity |
| Predicate | informationContained |
P12650
|
FINISHED |
| Object | patient name |
—
|
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 name | Statement: [NHS Dental Exemption Certificates, informationContained, patient name]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: informationContained Context triple: [NHS Dental Exemption Certificates, informationContained, patient name]
-
A.
typeOfInformation
Indicates that one entity specifies the category or kind of information that characterizes or describes another entity.
-
B.
providesInformationIn
Indicates that one entity supplies or conveys information within or through another entity or context.
-
C.
informationTypeHandled
Indicates that an entity is responsible for processing, managing, or dealing with a particular type or category of information.
-
D.
requiredInformation
chosen
Indicates that certain data or details are necessary and must be provided for a process, action, or relationship to proceed or be valid.
-
E.
collectsInformationOn
Indicates that one entity gathers or acquires data, facts, or details about another entity.
- 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_69c6880afb988190ad88011b48ecfcba |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d354177481908ab3cf5437c095e2 |
completed | March 27, 2026, 6:58 p.m. |
| PD | Predicate disambiguation | batch_69c6d08e8a2c8190ae4e8d8c039be7ce |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:08 p.m.