Triple
T38641131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TSMC N7P |
E938596
|
entity |
| Predicate | performanceGainOverPredecessor |
P82043
|
FINISHED |
| Object | up to 7% at same power |
—
|
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: up to 7% at same power | Statement: [TSMC N7P, performanceGainOverPredecessor, up to 7% at same power]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performanceGainOverPredecessor Context triple: [TSMC N7P, performanceGainOverPredecessor, up to 7% at same power]
-
A.
comparedToPredecessor
chosen
Indicates that something is being evaluated or measured in relation to the thing that came immediately before it.
-
B.
typicalEfficiencyComparedToPredecessor
Indicates how the usual or average efficiency of something compares to that of its predecessor.
-
C.
performanceBasis
Indicates that one entity’s performance is evaluated, determined, or justified on the basis of another specified factor, standard, or reference.
-
D.
performanceVariable
Indicates that one entity represents a measurable factor or parameter that influences or characterizes the performance of another entity.
-
E.
performanceImprovementReason
Indicates the reason or cause behind an observed or intended improvement in performance.
- 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_69f76ed948ec81908ce7811608a8f359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff7ae5d088819089aa3b6360b6b749 |
completed | May 9, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69ff7a4df6488190bf60d675b36b1d6d |
completed | May 9, 2026, 6:17 p.m. |
Created at: May 3, 2026, 4:32 p.m.