Triple
T7874726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adam optimizer |
E182821
|
entity |
| Predicate | parameterUpdateDependsOn |
P7002
|
FINISHED |
| Object | current gradient |
—
|
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: current gradient | Statement: [Adam optimizer, parameterUpdateDependsOn, current gradient]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parameterUpdateDependsOn Context triple: [Adam optimizer, parameterUpdateDependsOn, current gradient]
-
A.
conceptuallyDependsOn
Indicates that one entity’s definition, validity, or understanding relies on or is grounded in the concepts provided by another entity.
-
B.
positionDependsOn
Indicates that the spatial or ordered position of one entity is determined or constrained by the position of another entity.
-
C.
isUpdatedWhen
Indicates that one entity undergoes a change or refresh whenever another specified entity is modified or updated.
-
D.
hasUpdatePolicy
chosen
Indicates that one entity defines or is associated with the rules or strategy governing how another entity is updated or maintained over time.
-
E.
metricDependsOn
Indicates that the value or definition of one metric is determined by, derived from, or otherwise reliant on another metric.
- 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_69ca828a17248190b46defe758bc5ad3 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb39a961188190b2f12f8fe5d66641 |
completed | March 31, 2026, 3:04 a.m. |
| PD | Predicate disambiguation | batch_69cae928e1b88190b0620f4c4f03bc7d |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:56 p.m.