Triple
T5894141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Solvency II Directive |
E131061
|
entity |
| Predicate | policyholderProtection |
P957
|
FINISHED |
| Object | high level of consumer protection |
—
|
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: high level of consumer protection | Statement: [Solvency II Directive, policyholderProtection, high level of consumer protection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policyholderProtection Context triple: [Solvency II Directive, policyholderProtection, high level of consumer protection]
-
A.
policyName
Indicates the specific name or title assigned to a policy associated with an entity.
-
B.
protects
Indicates taking action to keep someone or something safe from harm, danger, or negative effects.
-
C.
protectedBy
chosen
Indicates that one entity provides protection, defense, or safeguarding for another entity.
-
D.
policyOutput
Indicates that a policy or decision-making process produces or yields a particular outcome, result, or output.
-
E.
guaranteeCoverage
Indicates that one party commits to providing financial or protective coverage for another party or specified situation.
- 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_69c00857439c819095950754176aa58a |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0400f1af881908d376ea4793f6dea |
completed | March 22, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69c0334dc8248190b7394dcece362d52 |
completed | March 22, 2026, 6:22 p.m. |
Created at: March 22, 2026, 3:58 p.m.