Triple
T36467648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wigner semicircle law |
E898462
|
entity |
| Predicate | hasConvergenceType |
P14357
|
FINISHED |
| Object | almost sure convergence |
—
|
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: almost sure convergence | Statement: [Wigner semicircle law, hasConvergenceType, almost sure convergence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasConvergenceType Context triple: [Wigner semicircle law, hasConvergenceType, almost sure convergence]
-
A.
hasConvergenceDomain
Indicates the domain or set of conditions under which a given process, function, or sequence converges.
-
B.
convergenceProperty
chosen
Indicates that one entity has a convergence-related characteristic or behavior with respect to another entity, such as approaching a limit or stabilizing under repeated application.
-
C.
hasConcretionType
Indicates that an entity possesses or is associated with a specific type or category of concretion.
-
D.
formedByConvergenceOf
Indicates that something comes into existence or is created as a result of multiple elements, paths, or processes coming together and uniting.
-
E.
hasNumberOfConvergingAvenues
Indicates the number of distinct avenues that meet or converge at a particular location or junction.
- 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_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0bf4b88190bdcfae9a14b51f0a |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:10 p.m.