Triple
T36490265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reformer architecture |
E899032
|
entity |
| Predicate | attentionRestriction |
P175148
|
FINISHED |
| Object | within hash buckets |
—
|
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: within hash buckets | Statement: [Reformer architecture, attentionRestriction, within hash buckets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attentionRestriction Context triple: [Reformer architecture, attentionRestriction, within hash buckets]
-
A.
notableRestriction
Indicates that there is a significant limitation, constraint, or prohibition that meaningfully affects the entity or its use.
-
B.
oftenRestrictedTo
Indicates that the use, occurrence, or applicability of something is frequently limited to a particular subset, context, or condition.
-
C.
restrictTo
chosen
Indicates that one entity limits or confines another entity’s scope, access, or applicability to a specified subset, condition, or context.
-
D.
restrictionLevel
Indicates the degree or strictness of limitations or constraints imposed on an entity, action, or access.
-
E.
contentRestriction
Indicates that access to or use of certain content is limited or controlled based on specified rules or conditions.
- 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_69f7c777e924819081a6634f549fe552 |
completed | May 3, 2026, 10:08 p.m. |
| PD | Predicate disambiguation | batch_69f7c477a4d481908f52e55b6688f60c |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:10 p.m.