Triple
T18520227
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CyberTipline |
E452563
|
entity |
| Predicate | handlesData |
P71354
|
FINISHED |
| Object | personally identifiable information of victims |
—
|
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: personally identifiable information of victims | Statement: [CyberTipline, handlesData, personally identifiable information of victims]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: handlesData Context triple: [CyberTipline, handlesData, personally identifiable information of victims]
-
A.
handlingProperty
Indicates that one entity specifies how another entity should be handled, processed, or treated under certain conditions.
-
B.
handledWith
Indicates that an entity is managed, processed, or dealt with using a particular method, tool, or means.
-
C.
handlesAgent
Indicates that one entity is responsible for managing, dealing with, or taking care of another entity (the agent).
-
D.
handlesHardware
Indicates that one entity is responsible for managing, operating, or working with hardware for another entity or within a given context.
-
E.
handledMatter
chosen
Indicates that an entity has dealt with, managed, or taken responsibility for a particular matter, issue, or case.
- 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_69d8d386df84819092355ebb260d848e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5338db5e4819086503a2176dfe499 |
completed | April 19, 2026, 7:57 p.m. |
| PD | Predicate disambiguation | batch_69e469e0025c81908f16ed4f922674af |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:37 a.m.