Triple
T11425407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Suffren-class nuclear attack submarines |
E270733
|
entity |
| Predicate | launchedFirstUnit |
P99233
|
FINISHED |
| Object | 2019 |
—
|
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: 2019 | Statement: [Suffren-class nuclear attack submarines, launchedFirstUnit, 2019]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: launchedFirstUnit Context triple: [Suffren-class nuclear attack submarines, launchedFirstUnit, 2019]
-
A.
firstSuccessfulLaunchDate
Indicates the calendar date on which an entity achieved its first successful launch.
-
B.
launchedAt
Indicates the specific time or event at which something (such as a product, project, or mission) was initiated or set into operation.
-
C.
launchedWith
Indicates that one entity was initiated, started, or set into motion together with another entity as part of the same launch event.
-
D.
launchedTo
Indicates that one entity has been sent or propelled from its origin toward a specific target or destination.
-
E.
firstDeployedIn
Indicates the time or place where something (such as a system, product, or technology) was initially put into operational use or service.
- F. None of above. chosen
Provenance (4 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_69d6aadeef688190874bcecd88b3dd9b |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d806be9c2c819084da13101cbb6c81 |
completed | April 9, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69d7e71436f88190ac7e45a04ea5c987 |
completed | April 9, 2026, 5:51 p.m. |
| PDg | Predicate description generation | batch_69d80010712c819089ea2e31e664abe1 |
completed | April 9, 2026, 7:37 p.m. |
Created at: April 8, 2026, 9:35 p.m.