Triple
T17081412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Operation Anvil |
E414476
|
entity |
| Predicate | nuclearTestProgram |
P71692
|
FINISHED |
| Object | United States nuclear testing program |
—
|
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: United States nuclear testing program | Statement: [Operation Anvil, nuclearTestProgram, United States nuclear testing program]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nuclearTestProgram Context triple: [Operation Anvil, nuclearTestProgram, United States nuclear testing program]
-
A.
nuclearWeaponsProgram
Indicates the existence, development, or pursuit of a program related to the research, production, or maintenance of nuclear weapons.
-
B.
nuclearTestSeries
chosen
Indicates a relationship where multiple nuclear tests are grouped and conducted as part of a coordinated series or campaign.
-
C.
nuclearTestTarget
Indicates that an entity is the target or location where a nuclear test is conducted.
-
D.
nuclearTestsConducted
Indicates that one entity has carried out nuclear weapons tests involving another entity, location, or time period.
-
E.
numberOfNuclearTests
Indicates the total count of nuclear tests associated with a given entity (such as a country, site, or time period).
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbe2fe7c819099ab0586b1a119f6 |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d642f74819098c014135e249b27 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:34 a.m.