Triple
T7936056
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EISA |
E184290
|
entity |
| Predicate | performanceComparedToISA |
P66611
|
FINISHED |
| Object | higher throughput than ISA |
—
|
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: higher throughput than ISA | Statement: [EISA, performanceComparedToISA, higher throughput than ISA]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performanceComparedToISA Context triple: [EISA, performanceComparedToISA, higher throughput than ISA]
-
A.
hasBaseISA
Indicates that an entity’s base or fundamental type is a specified ISA (Instruction Set Architecture) or foundational classification.
-
B.
comparesArchitectureTo
chosen
Indicates that one entity evaluates or contrasts the structure, design, or architectural characteristics of another entity against a reference or alternative architecture.
-
C.
performanceModel
Indicates a relationship where one entity serves as a performance model that represents, predicts, or characterizes the performance behavior of another entity.
-
D.
instructionSetSize
Indicates the size or number of instructions defined in an instruction set.
-
E.
performanceMeasurement
Indicates the act of assessing, quantifying, or evaluating how well an entity, process, or system performs against defined criteria or objectives.
- 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_69ca8290c21c8190906a5ca6fe2b03c4 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3aede3cc81908b0d3b54e68997b9 |
completed | March 31, 2026, 3:09 a.m. |
| PD | Predicate disambiguation | batch_69cae9335f288190ba96781fd6576a2b |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:08 p.m.