Triple
T35689776
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chinese restaurant process |
E1031255
|
entity |
| Predicate | clusterSizeDistribution |
P183822
|
FINISHED |
| Object | power-law-like behavior under Pitman–Yor generalization |
—
|
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: power-law-like behavior under Pitman–Yor generalization | Statement: [Chinese restaurant process, clusterSizeDistribution, power-law-like behavior under Pitman–Yor generalization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clusterSizeDistribution Context triple: [Chinese restaurant process, clusterSizeDistribution, power-law-like behavior under Pitman–Yor generalization]
-
A.
clusterSizeAffects
Indicates that the size of a cluster has an influence or impact on another property, behavior, or outcome.
-
B.
clusterSizeRange
Indicates the range of allowable or observed sizes for a given cluster within a specified context.
-
C.
clusterConcentration
Indicates how densely the elements within a cluster are packed or distributed relative to one another.
-
D.
clusterShape
Indicates the geometric form or configuration that a cluster of related items or points takes.
-
E.
clusterDensity
Indicates the degree to which elements within a cluster are closely packed or concentrated relative to its size or volume.
- F. None of above. chosen
Provenance (4 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_69f76e0c73ec819080ab60a9e2f5f1f6 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a34f8ee08190a040304635539a8f |
completed | May 3, 2026, 7:34 p.m. |
| PD | Predicate disambiguation | batch_69f7a06f125c8190843af194f042a465 |
completed | May 3, 2026, 7:22 p.m. |
| PDg | Predicate description generation | batch_69f7a34e80dc8190980d5b7b0b91341d |
completed | May 3, 2026, 7:34 p.m. |
Created at: May 3, 2026, 4:05 p.m.