Triple
T32342312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Redoutable-class submarine |
E826350
|
entity |
| Predicate | museumShipFromClass |
P160292
|
FINISHED |
| Object | French submarine Redoutable (S611) |
—
|
NE NERFINISHED |
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: French submarine Redoutable (S611) | Statement: [Redoutable-class submarine, museumShipFromClass, French submarine Redoutable (S611)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: museumShipFromClass Context triple: [Redoutable-class submarine, museumShipFromClass, French submarine Redoutable (S611)]
-
A.
hasMuseumShip
Indicates that one entity possesses or is associated with a museum ship, typically a preserved vessel displayed for public exhibition.
-
B.
becameMuseumShip
Indicates that a vessel or ship was converted from active service into a museum exhibit open to the public.
-
C.
classOnShip
Indicates that an entity holds a particular class or status aboard a ship.
-
D.
shipClass
Indicates the classification or type category to which a particular ship belongs.
-
E.
hasShipInClass
chosen
Indicates that an entity possesses or includes at least one ship that belongs to a specified ship class.
- 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_69f34914dfc48190a390cd0720d9e86f |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6be25253881908d83f1028bfc90a9 |
completed | May 3, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69f6b633e0c88190a727bb7d2751e2d5 |
completed | May 3, 2026, 2:43 a.m. |
Created at: May 1, 2026, 12:48 a.m.