Triple
T9674988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MXNet |
E234123
|
entity |
| Predicate | supportsCheckpoint |
P30109
|
FINISHED |
| Object | model parameters |
—
|
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: model parameters | Statement: [MXNet, supportsCheckpoint, model parameters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsCheckpoint Context triple: [MXNet, supportsCheckpoint, model parameters]
-
A.
hadCheckpoint
Indicates that an entity passed through, reached, or was associated with a specific checkpoint at some point in time.
-
B.
hasCheckpointControl
Indicates that one entity exercises control, management, or authority over a checkpoint associated with another entity.
-
C.
wasCheckpointName
Indicates that an entity previously had a specific checkpoint name assigned to it.
-
D.
hasCheckpoint
chosen
Indicates that an entity includes, contains, or is associated with one or more intermediate control or verification points within its structure, process, or path.
-
E.
supportsPersistence
Indicates that one entity enables or provides the capability for another entity’s data or state to be stored and retained over time.
- 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_69ca848f55e48190b3f67252571c3d45 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9c6d6dd48190a77c486337a58cb6 |
completed | April 1, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b5d40c8190850ad7a351445f32 |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:15 p.m.