Triple
T11217834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Force océanique stratégique |
E265482
|
entity |
| Predicate | mainAsset |
P3744
|
FINISHED |
| Object | ballistic missile submarine |
—
|
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: ballistic missile submarine | Statement: [Force océanique stratégique, mainAsset, ballistic missile submarine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainAsset Context triple: [Force océanique stratégique, mainAsset, ballistic missile submarine]
-
A.
mainAssetManaged
Indicates that one entity is responsible for managing another entity that serves as the primary or main asset.
-
B.
primaryAsset
chosen
Indicates that one entity is the main or most important asset associated with another entity.
-
C.
hasMajorAsset
Indicates that an entity possesses or controls a primary or most significant asset.
-
D.
mediaAssets
Indicates a relationship where one entity is associated with one or more media-related resources or files (such as images, videos, or audio).
-
E.
primaryFile
Indicates that one file in a set is designated as the main or most important file associated with a given entity 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_69d6aac59460819089b9848b27f57848 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8ea19e8819095d5d02c1f145534 |
completed | April 9, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69d75cfbbb188190861efd5d94fe27da |
completed | April 9, 2026, 8:02 a.m. |
Created at: April 8, 2026, 9:30 p.m.