Triple
T3244610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SPARC |
E68040
|
entity |
| Predicate | registerFile |
P46787
|
FINISHED |
| Object | 32 general-purpose registers per window |
—
|
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: 32 general-purpose registers per window | Statement: [SPARC, registerFile, 32 general-purpose registers per window]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: registerFile Context triple: [SPARC, registerFile, 32 general-purpose registers per window]
-
A.
registryFunction
Indicates a function that is responsible for registering or recording entities, configurations, or events within a registry or central management system.
-
B.
fileManager
Indicates a relationship where an entity manages, organizes, or controls access to files or file-related operations for another entity.
-
C.
registerModel
Indicates the action of adding or enrolling a model into a system or registry so it becomes recognized and available for use.
-
D.
uploader
Indicates that an entity is the one who uploads or has uploaded a particular item or resource.
-
E.
register
Indicates that an entity formally records or enrolls another entity or itself in an official system, list, or record.
- 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_69ad858e4c708190aa31d486cfee8a6a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf1982448190b3d60c9e4471421f |
completed | March 8, 2026, 5:17 p.m. |
| PD | Predicate disambiguation | batch_69ada41837e48190933572165be0ca38 |
completed | March 8, 2026, 4:30 p.m. |
| PDg | Predicate description generation | batch_69ada525bb2c8190b773efe6d696b6ab |
completed | March 8, 2026, 4:34 p.m. |
Created at: March 8, 2026, 3:08 p.m.