Triple
T10041601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stridsvagn 122 |
E205307
|
entity |
| Predicate | armorEnhancement |
P32307
|
FINISHED |
| Object | improved frontal turret armor compared to Leopard 2A5 |
—
|
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: improved frontal turret armor compared to Leopard 2A5 | Statement: [Stridsvagn 122, armorEnhancement, improved frontal turret armor compared to Leopard 2A5]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armorEnhancement Context triple: [Stridsvagn 122, armorEnhancement, improved frontal turret armor compared to Leopard 2A5]
-
A.
armorFeature
chosen
Indicates that one entity is a functional or descriptive feature of another entity’s armor.
-
B.
armorType
Indicates the specific category or classification of protective armor associated with an entity.
-
C.
armourProtection
Indicates that one entity provides protective armor or defensive covering for another entity.
-
D.
armour
Indicates that an entity provides protective covering or defense for another entity.
-
E.
armorProtectionLevel
Indicates the degree or rating of protective capability that armor provides against threats or damage.
- 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_69ca834f70e88190b2d74828b7767ec1 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cdcee48d8c8190af7c93b60f8ca7cb |
completed | April 2, 2026, 2:05 a.m. |
| PD | Predicate disambiguation | batch_69cd4b8d2280819089de27e57babd1f3 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 8:55 p.m.