Triple
T25741648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FMA3 |
E648231
|
entity |
| Predicate | effectOnPower |
P40373
|
FINISHED |
| Object | can improve energy efficiency per floating-point operation |
—
|
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: can improve energy efficiency per floating-point operation | Statement: [FMA3, effectOnPower, can improve energy efficiency per floating-point operation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectOnPower Context triple: [FMA3, effectOnPower, can improve energy efficiency per floating-point operation]
-
A.
heroPowerEffect
Indicates the specific impact or outcome that a hero’s power has when it is used.
-
B.
effectOnOutput
Indicates how one factor, action, or condition influences or changes the resulting output of a process or system.
-
C.
usesPowerFor
Indicates that one entity applies or exploits a particular power, energy, or capability for a specific purpose or activity.
-
D.
effectOnSystem
chosen
Indicates the influence, change, or impact that one entity, action, or condition has on the state or behavior of a system.
-
E.
enhancesPowersOf
Indicates that one entity increases, amplifies, or strengthens the abilities or powers of another entity.
- 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_69e7ab306eec8190b05c312c6ab186b8 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6430a93a48190854ce71df680b2fa |
completed | May 2, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69f641da05b881909f6283c988639c53 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 22, 2026, 3:45 a.m.