Triple
T24450216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Out of My Depth |
E616512
|
entity |
| Predicate | relatedToCrime |
P96742
|
FINISHED |
| Object | fraud |
—
|
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: fraud | Statement: [Out of My Depth, relatedToCrime, fraud]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedToCrime Context triple: [Out of My Depth, relatedToCrime, fraud]
-
A.
isRelatedCriminalMatterOf
Indicates that one legal case or issue is connected to, arises from, or is otherwise associated with another in a criminal context.
-
B.
committedCrime
Indicates that an entity has carried out or been responsible for a criminal act or offense.
-
C.
hasRelationshipToPerpetrator
Indicates that an entity has a specified type of relationship or connection to the perpetrator of an act or event.
-
D.
criminalType
chosen
Indicates the specific category or classification of crime associated with a criminal act or offender.
-
E.
relatedToClaimOf
Indicates a relationship where something is connected or pertinent to a specific claim or assertion.
- 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_69e2d7edca608190aafefc8877a1b4da |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f298574dd48190813a7c82b7012600 |
completed | April 29, 2026, 11:46 p.m. |
| PD | Predicate disambiguation | batch_69f287d3237c819099559c00f83131d8 |
completed | April 29, 2026, 10:36 p.m. |
Created at: April 18, 2026, 2:18 a.m.