Triple
T4470320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ACKTR |
E98477
|
entity |
| Predicate | usesGradientInformation |
P56721
|
FINISHED |
| Object | curvature-aware updates |
—
|
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: curvature-aware updates | Statement: [ACKTR, usesGradientInformation, curvature-aware updates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesGradientInformation Context triple: [ACKTR, usesGradientInformation, curvature-aware updates]
-
A.
averageGradient
Indicates the mean rate of change (slope) of a quantity over a specified interval or region.
-
B.
maximumGradient
Indicates the greatest rate of change or steepest slope that occurs within a given function, surface, or dataset.
-
C.
hasColorInfo
Indicates that an entity is associated with specific color-related information or attributes.
-
D.
usesColorDifferenceSignals
Indicates that one entity employs differences in color as signals to convey information or communicate.
-
E.
usesLightingFor
Indicates that one entity employs or relies on a particular lighting setup, technology, or condition to achieve a purpose or perform an action.
- 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_69b3454b4ae481908967426dd37284d6 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b356fb69a0819099f0005779f4fcac |
completed | March 13, 2026, 12:14 a.m. |
| PD | Predicate disambiguation | batch_69b3563bf4f8819081726cde3a34460b |
completed | March 13, 2026, 12:11 a.m. |
| PDg | Predicate description generation | batch_69b356f9afc48190acb50c45a310e072 |
completed | March 13, 2026, 12:14 a.m. |
Created at: March 12, 2026, 11:34 p.m.