Triple
T33027184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Electronic Codebook mode |
E845072
|
entity |
| Predicate | insecureFor |
P175701
|
FINISHED |
| Object | image encryption |
—
|
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: image encryption | Statement: [Electronic Codebook mode, insecureFor, image encryption]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: insecureFor Context triple: [Electronic Codebook mode, insecureFor, image encryption]
-
A.
insecureAbout
Indicates that one entity feels uncertain, self-doubting, or lacking confidence regarding some aspect of another entity or itself.
-
B.
isSecureFor
Indicates that one entity provides a level of protection or safety that makes it appropriate or safe for use, access, or interaction by another entity.
-
C.
isSecurityFor
Indicates that one entity serves as protection, safeguard, or collateral guaranteeing the obligations, value, or safety of another entity.
-
D.
previouslySafeFor
Indicates that something was considered safe for a particular entity or use at an earlier time, but that safety status may no longer hold.
-
E.
insecurityLinkedTo
Indicates a relationship where one entity’s insecurity is connected or attributed to another entity as a contributing factor or source.
- F. None of above. chosen
Provenance (4 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_69f34950749c8190ae05cd27adb16d58 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d74b20a48190900dda1014cc13a8 |
completed | May 3, 2026, 5:04 a.m. |
| PD | Predicate disambiguation | batch_69f6d27120988190aacec621cf2bf0e8 |
completed | May 3, 2026, 4:43 a.m. |
| PDg | Predicate description generation | batch_69f6d6a482fc8190b526291cd99b8696 |
completed | May 3, 2026, 5:01 a.m. |
Created at: May 1, 2026, 1:23 a.m.