Triple
T7874710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adam optimizer |
E182821
|
entity |
| Predicate | defaultBeta2 |
P79504
|
FINISHED |
| Object | 0.999 |
—
|
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: 0.999 | Statement: [Adam optimizer, defaultBeta2, 0.999]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defaultBeta2 Context triple: [Adam optimizer, defaultBeta2, 0.999]
-
A.
B_2
Indicates a secondary or alternative type of binary relationship between two entities, often used as a variant or refinement of a primary relation B.
-
B.
secondaryTo
Indicates that one condition, event, or factor occurs as a consequence of, or is caused by, another primary condition, event, or factor.
-
C.
secondaryEndpoint
Indicates that something serves as an additional, non-primary endpoint or target associated with a main endpoint in a relationship or process.
-
D.
secondarySetting
Indicates that an entity serves as an additional or supporting setting context for another entity, rather than being the primary setting.
-
E.
defaultOn
Indicates that something is in an enabled or active state by default, without requiring explicit activation.
- 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_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. |
| PDg | Predicate description generation | batch_69caf786ec748190b6347b0c94335550 |
completed | March 30, 2026, 10:21 p.m. |
Created at: March 30, 2026, 4:56 p.m.