Triple

T26408699
Position Surface form Disambiguated ID Type / Status
Subject Noekeon E663898 entity
Predicate roundTransformation P162804 FINISHED
Object Theta diffusion layer
The Theta diffusion layer is a linear mixing operation used within the Noekeon block cipher’s round function to rapidly spread input bit differences across the state for cryptographic diffusion.
 E1724462 NE FINISHED

How this triple was built (3 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: Theta diffusion layer | Statement: [Noekeon, roundTransformation, Theta diffusion layer]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Theta diffusion layer
Triple: [Noekeon, roundTransformation, Theta diffusion layer]
Generated description
The Theta diffusion layer is a linear mixing operation used within the Noekeon block cipher’s round function to rapidly spread input bit differences across the state for cryptographic diffusion.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: roundTransformation
Context triple: [Noekeon, roundTransformation, Theta diffusion layer]
  • A. round
    Indicates that an entity has a circular or approximately circular shape or form.
  • B. rounded
    Indicates that one entity has been made or become rounder or more curved in shape, often by smoothing or adjusting its edges or values.
  • C. roundOf
    Indicates that one event, match, or game occurs as a specific stage or phase within a larger competition or tournament.
  • D. roundFunctionInput
    Indicates that a given value is used as an input to a rounding function in a computation or process.
  • E. roundel
    Indicates that one entity bears, displays, or is marked with a circular emblem or symbol representing another entity.
  • F. None of above. chosen

Provenance (7 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_69ee883931888190901be96d75ee23cc completed April 26, 2026, 9:48 p.m.
NER Named-entity recognition batch_69f62e4168a48190b45268f922780da6 completed May 2, 2026, 5:02 p.m.
NED1 Entity disambiguation (via context triple) batch_6a11aeba42d88190b867fa6279dada9d completed May 23, 2026, 1:42 p.m.
NEDg Description generation batch_6a11af82fb088190bee576d403827a3e completed May 23, 2026, 1:45 p.m.
NED2 Entity disambiguation (via description) batch_6a11b02e363c8190926886514d5ba6a0 completed May 23, 2026, 1:48 p.m.
PD Predicate disambiguation batch_69f62c15952881908a5ea0c25904afec completed May 2, 2026, 4:53 p.m.
PDg Predicate description generation batch_69f62d5268ac8190835dc7119353b840 completed May 2, 2026, 4:58 p.m.
Created at: April 26, 2026, 11:36 p.m.