Triple
T32707091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rabin cryptosystem |
E836301
|
entity |
| Predicate | decryptionStep |
P34882
|
FINISHED |
| Object | compute square roots of c modulo p and q |
—
|
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: compute square roots of c modulo p and q | Statement: [Rabin cryptosystem, decryptionStep, compute square roots of c modulo p and q]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: decryptionStep Context triple: [Rabin cryptosystem, decryptionStep, compute square roots of c modulo p and q]
-
A.
decryptionProcess
chosen
Indicates the action or procedure of converting encrypted data back into its original, readable form using the appropriate decryption method or key.
-
B.
decryptionCodename
Indicates that one entity serves as the codename or label used for a particular decryption operation or process involving another entity.
-
C.
decryptionRule
Indicates a rule or method used to convert encrypted data back into its original, readable form.
-
D.
decryptionRequires
Indicates that performing decryption of some data depends on or needs a specified key, resource, or condition to be fulfilled.
-
E.
decryptionAmbiguity
Indicates that the result of a decryption process is not uniquely determined, allowing multiple plausible plaintexts or interpretations from the same encrypted data.
- 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_69f3493446148190819541f3ffe79975 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6cd126fcc8190aa1f1f146e45ec0c |
completed | May 3, 2026, 4:20 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:10 a.m.