Triple
T36467686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marchenko–Pastur law |
E898463
|
entity |
| Predicate | densityFormula |
P87492
|
FINISHED |
| Object | f(x) = (1 / (2π λ x)) sqrt((b - x)(x - a)) for x in [a,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: f(x) = (1 / (2π λ x)) sqrt((b - x)(x - a)) for x in [a,b] | Statement: [Marchenko–Pastur law, densityFormula, f(x) = (1 / (2π λ x)) sqrt((b - x)(x - a)) for x in [a,b]]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: densityFormula Context triple: [Marchenko–Pastur law, densityFormula, f(x) = (1 / (2π λ x)) sqrt((b - x)(x - a)) for x in [a,b]]
-
A.
givesDensityOf
chosen
Indicates that one entity provides or specifies the density value of another entity.
-
B.
formulaUsed
Indicates that a particular formula is employed or applied in performing a calculation, derivation, or reasoning step.
-
C.
densityLiquid
Indicates that the predicate specifies the mass per unit volume of a substance when it is in its liquid state.
-
D.
typeOfDensity
Indicates the specific category or kind of density (e.g., mass, population, charge) that characterizes a given quantity or measurement.
-
E.
dimensionFormula
Indicates a mathematical or logical expression that defines how a particular dimension (such as size, measure, or extent) is derived or calculated from other quantities.
- 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_69f76e58ebd88190b75d9b169b59d793 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bccf05bc8190b61fdb2b2a315811 |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:10 p.m.