Triple
T2002176
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daniel J. Bernstein |
E43494
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Salsa20/8 |
E42566
|
NE 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: Salsa20/8 | Statement: [Daniel J. Bernstein, notableWork, Salsa20/8]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salsa20/8 Context triple: [Daniel J. Bernstein, notableWork, Salsa20/8]
-
A.
Salsa20
chosen
Salsa20 is a high-speed stream cipher designed by Daniel J. Bernstein, widely used in modern cryptography for its strong security and efficient software performance.
-
B.
ChaCha20
ChaCha20 is a modern stream cipher designed by Daniel J. Bernstein, widely used for its high performance and strong security in protocols like TLS.
-
C.
Rijndael
Rijndael is a symmetric block cipher designed by Joan Daemen and Vincent Rijmen that was selected by NIST as the basis for the Advanced Encryption Standard (AES).
-
D.
Spritz cipher
Spritz cipher is a modern stream cipher and hash function designed by Ronald Rivest and Jacob Schuldt as a more secure and flexible successor to RC4.
-
E.
Poly1305
Poly1305 is a high-speed message authentication code (MAC) algorithm commonly used with stream ciphers like ChaCha20 to provide data integrity and authenticity.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88715dbbc8190b2299e29e955d997 |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8820cec8190a945e5daeb8c9df6 |
completed | March 7, 2026, 5:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae0adcd2708190b126e3872679d88c |
completed | March 8, 2026, 11:48 p.m. |
Created at: March 4, 2026, 7:37 p.m.