Triple
T12205694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NRU reactor |
E290829
|
entity |
| Predicate | worldShareOfMo99Production |
P99700
|
FINISHED |
| Object | about 30 percent at peak |
—
|
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: about 30 percent at peak | Statement: [NRU reactor, worldShareOfMo99Production, about 30 percent at peak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worldShareOfMo99Production Context triple: [NRU reactor, worldShareOfMo99Production, about 30 percent at peak]
-
A.
massProduced
Indicates that an item is manufactured in large quantities, typically using standardized, industrial production processes.
-
B.
totalProduction
Indicates the overall quantity of goods, services, or output produced by an entity or system over a specified period or within a defined scope.
-
C.
approximateProductionNumber
chosen
Indicates that one entity specifies an estimated or non-exact quantity associated with the production output of another entity.
-
D.
numberOfIsotopesProduced
Indicates the quantity of distinct isotopes that are generated or obtained from a specified process, reaction, or source.
-
E.
mainMetalProduced
Indicates that a location, facility, or process primarily produces a particular metal as its main output.
- 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_69d6ab65923081909acfc61b7a612233 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d920e312708190b4aede2e21f5f697 |
completed | April 10, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69d91c3d669c81908eea7ad61122d275 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:51 p.m.