Triple
T12796232
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Italian heavy cruiser Zara |
E305895
|
entity |
| Predicate | armorTurretThickness |
P27154
|
FINISHED |
| Object | up to about 150 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 150 mm | Statement: [Italian heavy cruiser Zara, armorTurretThickness, up to about 150 mm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armorTurretThickness Context triple: [Italian heavy cruiser Zara, armorTurretThickness, up to about 150 mm]
-
A.
armorTurretFaceThickness
chosen
Indicates the thickness of the armor on the front-facing surface of a turret.
-
B.
armourThickness
Indicates the measured thickness of an entity’s protective armor in the context of defense or shielding.
-
C.
deckArmorThickness
Indicates the thickness of the armor plating on the horizontal deck surface of a vehicle, vessel, or structure.
-
D.
armorThicknessMax
Indicates the maximum thickness of armor that an entity possesses or can withstand.
-
E.
armourConningTowerThickness
Indicates the thickness of the armor protecting a vessel’s conning tower.
- 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_69d7bdf366888190a8cccb982606889c |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e6db68481909a2ca8da1287f3e0 |
completed | April 10, 2026, 9:41 p.m. |
| PD | Predicate disambiguation | batch_69d9640ed7448190b276e7fab649f7d2 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:30 p.m.