Triple
T2058690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Health Insurance Commission |
E45735
|
entity |
| Predicate | typeOfInsurance |
P12185
|
FINISHED |
| Object | health insurance |
—
|
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: health insurance | Statement: [National Health Insurance Commission, typeOfInsurance, health insurance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfInsurance Context triple: [National Health Insurance Commission, typeOfInsurance, health insurance]
-
A.
insuranceType
chosen
Indicates the specific category or kind of insurance coverage associated with an entity or relationship.
-
B.
insurance
Indicates a relationship where one party provides financial protection or coverage to another against specified risks or losses, typically in exchange for payment.
-
C.
typeOfDiscriminationCovered
Indicates that a particular kind or category of discriminatory behavior is included within the scope of protections, rules, or analysis.
-
D.
typeOfClaim
Indicates the specific category or nature of a claim being made in relation to an entity or statement.
-
E.
planType
Indicates the specific category or kind of plan associated with an entity, such as its level, structure, or intended use.
- 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_69a8891a19508190a12ef1e192308dcb |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb9af42988190a4e977154dd10312 |
completed | March 7, 2026, 5:37 a.m. |
| PD | Predicate disambiguation | batch_69abb7ad5a7c8190b92575d6053b3fb7 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:40 p.m.