Triple
T1836092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rényi divergence |
E41069
|
entity |
| Predicate | equalsAt |
P7398
|
FINISHED |
| Object | Kullback–Leibler divergence when α = 1 |
—
|
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: Kullback–Leibler divergence when α = 1 | Statement: [Rényi divergence, equalsAt, Kullback–Leibler divergence when α = 1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: equalsAt Context triple: [Rényi divergence, equalsAt, Kullback–Leibler divergence when α = 1]
-
A.
isComparedTo
Indicates that one entity is evaluated or measured in relation to another to highlight similarities, differences, or relative qualities.
-
B.
hasEquivalent
chosen
Indicates that two entities are considered equal in value, meaning, or function within a given context.
-
C.
isAt
Indicates that one entity is located at or present in the place or position of another entity.
-
D.
coincidesWith
Indicates that two entities occupy the same position, time, or state such that they exactly overlap or occur together.
-
E.
modeEquals
Indicates that two compared entities share exactly the same mode or operational state.
- 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_69a88647f9388190909bc36e795bdaec |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb32d35508190bf1c487dffbecaf0 |
completed | March 7, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69abafd88ebc81908208394746351fe6 |
completed | March 7, 2026, 4:55 a.m. |
Created at: March 4, 2026, 7:33 p.m.