Triple
T19824154
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japanese battleship Tosa |
E476274
|
entity |
| Predicate | designedDeckArmorThickness |
P18833
|
FINISHED |
| Object | up to about 102 mm |
—
|
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: up to about 102 mm | Statement: [Japanese battleship Tosa, designedDeckArmorThickness, up to about 102 mm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designedDeckArmorThickness Context triple: [Japanese battleship Tosa, designedDeckArmorThickness, up to about 102 mm]
-
A.
deckArmorThickness
chosen
Indicates the thickness of the armor plating on the horizontal deck surface of a vehicle, vessel, or structure.
-
B.
armourThickness
Indicates the measured thickness of an entity’s protective armor in the context of defense or shielding.
-
C.
armourThicknessMin
Indicates the minimum measured or specified thickness of an object's armor in the described context.
-
D.
sideArmorThickness
Indicates the thickness of an object's armor specifically along its sides.
-
E.
armoredBeltThickness
Indicates the thickness of an entity’s protective armored belt in the context of its defensive structure or design.
- 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e655017c188190ae9e17ae6b0eee05 |
completed | April 20, 2026, 4:32 p.m. |
| PD | Predicate disambiguation | batch_69e5305bda388190a23b7191768107b1 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:50 p.m.