Triple
T20074555
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Omega laser system |
E499825
|
entity |
| Predicate | peakPowerClass |
P52649
|
FINISHED |
| Object | terawatt-class |
—
|
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: terawatt-class | Statement: [Omega laser system, peakPowerClass, terawatt-class]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: peakPowerClass Context triple: [Omega laser system, peakPowerClass, terawatt-class]
-
A.
powerClassBR
chosen
Indicates a relationship where one entity is classified or grouped according to its power-related category or level relative to another entity.
-
B.
speedClass
Indicates the categorical speed level or range assigned to an entity based on how fast it moves or operates.
-
C.
powerToWeightRatio
Indicates the relationship between an entity’s available power and its mass, expressing how much power is provided per unit of weight.
-
D.
typicalPower
Indicates the usual or characteristic amount of power associated with an entity under normal operating conditions.
-
E.
powerRange
Indicates the range of power values within which an entity operates, applies, or is considered valid.
- 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66439efe881909a068c3f05022421 |
completed | April 20, 2026, 5:36 p.m. |
| PD | Predicate disambiguation | batch_69e54cf369b88190931532420517dac7 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:40 p.m.