Triple
T6236730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bayes’ theorem |
E139495
|
entity |
| Predicate | coreFormula |
P2310
|
FINISHED |
| Object | P(A|B) = P(B|A) P(A) / P(B) |
—
|
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: P(A|B) = P(B|A) P(A) / P(B) | Statement: [Bayes’ theorem, coreFormula, P(A|B) = P(B|A) P(A) / P(B)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coreFormula Context triple: [Bayes’ theorem, coreFormula, P(A|B) = P(B|A) P(A) / P(B)]
-
A.
keyFormula
chosen
Indicates that a formula serves as the primary or defining expression associated with an entity or relationship.
-
B.
recitesFormula
Indicates that one entity verbally or mentally repeats a specific formula, such as a set phrase, equation, or ritual wording, typically from memory.
-
C.
formulaUsed
Indicates that a particular formula is employed or applied in performing a calculation, derivation, or reasoning step.
-
D.
mathematicallyExpressedBy
Indicates that something (such as a concept, quantity, or relationship) is represented or captured using a specific mathematical expression or formulation.
-
E.
regulationFormula
Indicates the specific rule or formula that governs how a process, behavior, or quantity is controlled or regulated.
- 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_69c008b0e7ac8190808a59573ee646f3 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063021258819093a9237041816638 |
completed | March 22, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69c05601de6481909d0880048fd7b49a |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:23 p.m.