Triple
T500081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French Armed Forces |
E10380
|
entity |
| Predicate | hasNuclearComponent |
P3063
|
FINISHED |
| Object | submarine-launched ballistic missiles |
—
|
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: submarine-launched ballistic missiles | Statement: [French Armed Forces, hasNuclearComponent, submarine-launched ballistic missiles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNuclearComponent Context triple: [French Armed Forces, hasNuclearComponent, submarine-launched ballistic missiles]
-
A.
hasNuclearWeapons
chosen
Indicates that the subject possesses or controls nuclear weapons.
-
B.
hasNuclearRole
Indicates that an entity participates in, is responsible for, or holds authority related to nuclear activities, functions, or capabilities.
-
C.
nuclearWeaponsState
Indicates that a state possesses, has developed, or is recognized as having nuclear weapons capabilities.
-
D.
isNucleusOfIsotope
Indicates that a given nucleus belongs to and characterizes a specific isotope.
-
E.
producedPlutoniumFor
Indicates that one entity generated or manufactured plutonium intended for use by 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_69a2e847df8481909239ec08ccf1e376 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f13096248190a622a58dcf540b00 |
completed | Feb. 28, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69a2edfbb7e0819092cf29c2c68fe8fb |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.