Triple
T18016529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mask R-CNN |
E431009
|
entity |
| Predicate | hasLossFunction |
P31982
|
FINISHED |
| Object | classification loss |
—
|
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: classification loss | Statement: [Mask R-CNN, hasLossFunction, classification loss]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLossFunction Context triple: [Mask R-CNN, hasLossFunction, classification loss]
-
A.
usesLossFunction
chosen
Indicates that one entity employs a particular loss function as part of its optimization or learning process.
-
B.
hasTrainingFunction
Indicates that one entity serves as a training function or mechanism for another entity.
-
C.
hasLogisticFunction
Indicates that one entity is responsible for providing, managing, or supporting the logistics operations or services of another entity.
-
D.
hasEnergyFunction
Indicates that an entity is associated with, governed by, or characterized through a specific energy function.
-
E.
hasDamFunction
Indicates that something serves the role or performs the function of a dam, such as impounding or regulating the flow of water.
- 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b9be5d0c819097e006f32d98753a |
completed | April 19, 2026, 11:17 a.m. |
| PD | Predicate disambiguation | batch_69e3f904b8048190add43883cd7cb191 |
completed | April 18, 2026, 9:35 p.m. |
Created at: April 10, 2026, 10:24 a.m.