Triple
T27762341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Batch Normalization |
E701500
|
entity |
| Predicate | usesDuringInference |
P4341
|
FINISHED |
| Object | running mean |
—
|
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: running mean | Statement: [Batch Normalization, usesDuringInference, running mean]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesDuringInference Context triple: [Batch Normalization, usesDuringInference, running mean]
-
A.
usedToInfer
Indicates that one entity serves as a basis or source from which another entity is logically derived or concluded.
-
B.
supportsInferenceOf
Indicates that one entity provides a logical basis or justification for concluding or deriving another entity.
-
C.
usedDuring
chosen
Indicates that one entity is employed, applied, or active in the course of another entity’s process, event, or time period.
-
D.
usesHeuristics
Indicates that an entity relies on heuristic methods or rules of thumb, rather than exhaustive or optimal procedures, to make decisions or solve problems.
-
E.
inferredLaterUse
Indicates that something is deduced or predicted to be used at a subsequent time based on available information or context.
- 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_69ef6a5193808190816eb7d0020b2d87 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 27, 2026, 4:28 p.m.