Triple
T18204937
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Longformer |
E435878
|
entity |
| Predicate | attentionPattern |
P31647
|
FINISHED |
| Object | sparse 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: sparse attention | Statement: [Longformer, attentionPattern, sparse attention]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attentionPattern Context triple: [Longformer, attentionPattern, sparse attention]
-
A.
focusType
chosen
Indicates the specific kind or category of focus or attention that is being applied to or associated with an entity or interaction.
-
B.
accessPattern
Indicates how an entity interacts with or retrieves data or resources, such as the manner, frequency, or sequence of access.
-
C.
pattern
Indicates that one entity exhibits, follows, or is characterized by a particular recurring form, structure, or arrangement associated with another entity.
-
D.
traditionalFocus
Indicates a focus on preserving, emphasizing, or adhering to long-established customs, practices, or conventions within a given context.
-
E.
focusesOn
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e222831081908f7d5500424e3acb |
completed | April 19, 2026, 2:09 p.m. |
| PD | Predicate disambiguation | batch_69e4332155d88190b106d0dceb4554af |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:32 a.m.