Triple
T36467871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ginibre ensemble |
E898467
|
entity |
| Predicate | matrixEntriesDistribution |
P128207
|
FINISHED |
| Object | independent Gaussian entries |
—
|
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: independent Gaussian entries | Statement: [Ginibre ensemble, matrixEntriesDistribution, independent Gaussian entries]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: matrixEntriesDistribution Context triple: [Ginibre ensemble, matrixEntriesDistribution, independent Gaussian entries]
-
A.
entryDistribution
chosen
Indicates how entries are allocated, spread, or assigned across a set of targets or categories.
-
B.
classDistribution
Indicates how instances are proportionally or numerically distributed across different classes or categories within a dataset or grouping.
-
C.
ballDistribution
Indicates the allocation or sharing of balls among participants or locations within a given context.
-
D.
distributionPattern
Indicates the characteristic way in which something is spread, arranged, or allocated across a space, group, or set.
-
E.
distributesOn
Indicates that one entity allocates, spreads, or apportions something across or onto another entity or set of entities.
- 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_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b91fd88190ab85afd626603769 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:10 p.m.