Triple
T9932107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ed25519 |
E192669
|
entity |
| Predicate | curveEquation |
P91201
|
FINISHED |
| Object | -x^2 + y^2 = 1 + dx^2y^2 over GF(2^255 - 19) |
—
|
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: -x^2 + y^2 = 1 + dx^2y^2 over GF(2^255 - 19) | Statement: [Ed25519, curveEquation, -x^2 + y^2 = 1 + dx^2y^2 over GF(2^255 - 19)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: curveEquation Context triple: [Ed25519, curveEquation, -x^2 + y^2 = 1 + dx^2y^2 over GF(2^255 - 19)]
-
A.
polarEquation
Indicates that a mathematical relationship is expressed as an equation in polar coordinates, relating a radius and angle rather than Cartesian coordinates.
-
B.
relatedCurve
Indicates that one curve is associated with or derived from another curve in a defined relational way.
-
C.
curveOrder
Indicates the specific sequence or ranking assigned to curves within a set or system.
-
D.
curveCondition
Indicates that a specific condition or constraint applies to a curve, such as its shape, smoothness, or allowable parameter range.
-
E.
hasPolarEquation
Indicates that an entity is associated with, or can be represented by, a specific equation expressed in polar coordinates.
- 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_69ca82dd978c8190947124ab0d3315ac |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5b54f348190b8e70e7beff6098a |
completed | April 2, 2026, 12:17 a.m. |
| PD | Predicate disambiguation | batch_69cd1d9428cc81909b4b4938566d78a7 |
completed | April 1, 2026, 1:28 p.m. |
| PDg | Predicate description generation | batch_69cd3581a9688190a00cef4c3eebb0ae |
completed | April 1, 2026, 3:10 p.m. |
Created at: March 30, 2026, 8:43 p.m.