Triple
T20490419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Devonshire-class armoured cruiser |
E502727
|
entity |
| Predicate | hasArmamentLayout |
P101195
|
FINISHED |
| Object | main guns mounted in turrets |
—
|
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: main guns mounted in turrets | Statement: [Devonshire-class armoured cruiser, hasArmamentLayout, main guns mounted in turrets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasArmamentLayout Context triple: [Devonshire-class armoured cruiser, hasArmamentLayout, main guns mounted in turrets]
-
A.
primaryArmamentLayout
Indicates how the main weapons or primary armament of an entity are arranged or distributed relative to that entity.
-
B.
armamentConfiguration
chosen
Indicates how weapons or armaments are arranged, equipped, or configured on an entity in a given context.
-
C.
gunDeckArmament
Indicates the type or configuration of weapons mounted on a ship’s gun deck.
-
D.
armamentCapacity
Indicates the maximum quantity or type of weapons or munitions that something is designed or allowed to carry.
-
E.
armamentFlexible
Indicates that an entity’s armament or weapon configuration can be adjusted, reconfigured, or adapted to different setups or roles.
- 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_69e0b4b0373881909dd3e9387f82eab4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69cb8e7848190a1dc497a10ae798c |
completed | April 20, 2026, 9:38 p.m. |
| PD | Predicate disambiguation | batch_69e59fcdf6e08190a604204615dc56e6 |
completed | April 20, 2026, 3:38 a.m. |
Created at: April 16, 2026, 11:35 a.m.