Triple
T36490263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reformer architecture |
E899032
|
entity |
| Predicate | usesSorting |
P144284
|
FINISHED |
| Object | hash buckets for attention |
—
|
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: hash buckets for attention | Statement: [Reformer architecture, usesSorting, hash buckets for attention]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesSorting Context triple: [Reformer architecture, usesSorting, hash buckets for attention]
-
A.
hasSort
Indicates that one entity is associated with, or classified by, a particular sort, type, or category.
-
B.
hasSortingInfrastructure
Indicates that an entity possesses systems or facilities specifically designed for organizing, classifying, or arranging items according to defined criteria.
-
C.
supportsOnlineSorting
Indicates that the subject provides functionality for arranging items or data in different orders through an online or digital interface.
-
D.
sortingMethod
chosen
Indicates the technique or criterion used to order a set of items relative to one another.
-
E.
isComparisonSort
Indicates that the sorting algorithm operates by comparing pairs of elements to determine their order.
- 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_69f76e5ad4588190bdbce60c52fbb785 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fdb04ed81c8190b8feea90c1c785a6 |
completed | May 8, 2026, 9:43 a.m. |
| PD | Predicate disambiguation | batch_69fda9d6c5148190a63205b6d9b0a1b4 |
completed | May 8, 2026, 9:16 a.m. |
Created at: May 3, 2026, 4:10 p.m.