Triple
T26409149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GHASH |
E663911
|
entity |
| Predicate | collisionProbabilityBound |
P96513
|
FINISHED |
| Object | proportional to number of blocks squared divided by 2^128 |
—
|
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: proportional to number of blocks squared divided by 2^128 | Statement: [GHASH, collisionProbabilityBound, proportional to number of blocks squared divided by 2^128]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collisionProbabilityBound Context triple: [GHASH, collisionProbabilityBound, proportional to number of blocks squared divided by 2^128]
-
A.
boundedByApprox
Indicates that one quantity is constrained by another within an approximate or tolerance-based bound, rather than an exact strict limit.
-
B.
hasFailureProbability
Indicates that an entity is associated with a likelihood or chance that it will fail within a given context or conditions.
-
C.
givesBoundOn
chosen
Indicates that one quantity provides an upper or lower limit (a bound) on the value or behavior of another quantity.
-
D.
junctionCountApprox
Indicates an approximate count of junctions or connection points involved in or associated with the given entities.
-
E.
circularErrorProbable
Indicates the radius within which a projectile or system is expected to land or perform with a specified probability, typically 50%, relative to a target point.
- 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_69ee883931888190901be96d75ee23cc |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f610faa77081908956b6e8b5b1570c |
completed | May 2, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69f5f800fa9c8190aab0962669fde8ac |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 11:37 p.m.