Triple
T16657322
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Client Security Fund |
E404763
|
entity |
| Predicate | typeOfMisconductCovered |
P93292
|
FINISHED |
| Object | theft of client funds |
—
|
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: theft of client funds | Statement: [Client Security Fund, typeOfMisconductCovered, theft of client funds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfMisconductCovered Context triple: [Client Security Fund, typeOfMisconductCovered, theft of client funds]
-
A.
typeOfViolationsCovered
chosen
Indicates the kinds or categories of violations that are included within the scope of a rule, policy, agreement, or enforcement action.
-
B.
concernsTypeOfConduct
Indicates that something is about or relates specifically to a particular type or category of conduct or behavior.
-
C.
accusationType
Indicates the specific category or nature of an accusation made by one party against another.
-
D.
hasTransgression
Indicates that one entity has committed, is responsible for, or is associated with a violation, offense, or wrongdoing in relation to another entity or rule.
-
E.
typeOfCensure
Indicates the specific kind or category of censure applied in a given disciplinary or critical action.
- 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_69d8838b5fbc81908c6575c132b82e80 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37bfbfd7c819092c92f6c8da07dbd |
completed | April 18, 2026, 12:41 p.m. |
| PD | Predicate disambiguation | batch_69e319b1d7f08190b5ecb4a68c636c15 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:18 a.m.