Triple
T11181084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Ignition Facility |
E264537
|
entity |
| Predicate | ignitionEnergyGain |
P17457
|
FINISHED |
| Object | fusion energy output exceeded laser energy input |
—
|
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: fusion energy output exceeded laser energy input | Statement: [National Ignition Facility, ignitionEnergyGain, fusion energy output exceeded laser energy input]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ignitionEnergyGain Context triple: [National Ignition Facility, ignitionEnergyGain, fusion energy output exceeded laser energy input]
-
A.
energyContribution
Indicates the amount or role of energy that one entity provides or contributes to another entity, process, or system.
-
B.
energyConcentration
Indicates a relationship where energy is gathered, focused, or accumulated within a specific region, object, or system.
-
C.
ignitionMethod
Indicates the specific way or mechanism by which something is ignited or set on fire.
-
D.
outputEnergy
chosen
Indicates that an entity produces or releases a certain amount or form of energy as a result of its operation or behavior.
-
E.
energyLevel
Indicates the amount or intensity of energy possessed, produced, or exhibited by an entity in a given state or context.
- 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_69d6aa9dafac8190bd90d2c74f661aa7 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8a7f35481909f35feb94ef10e80 |
completed | April 9, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69d75cf4461c8190af84060f7db83211 |
completed | April 9, 2026, 8:01 a.m. |
Created at: April 8, 2026, 9:29 p.m.