Triple
T10976823
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stora riksvapnet |
E259390
|
entity |
| Predicate | hasMantling |
P79547
|
FINISHED |
| Object | royal ermine mantle |
—
|
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: royal ermine mantle | Statement: [Stora riksvapnet, hasMantling, royal ermine mantle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMantling Context triple: [Stora riksvapnet, hasMantling, royal ermine mantle]
-
A.
mantlingLined
Indicates that the inner surface of a heraldic mantling is lined with a specified material, color, or pattern.
-
B.
hasRevetment
Indicates that a structure, surface, or area is provided with a protective revetment (such as a retaining or facing layer) to resist erosion, impact, or structural failure.
-
C.
hasLiningMaterial
chosen
Indicates that one entity uses or contains another entity as the material forming its inner lining.
-
D.
hasCornice
Indicates that one entity (typically a building or structure) possesses a cornice as an architectural feature.
-
E.
hasDomeDecoration
Indicates that an entity’s dome is adorned with specific decorative elements or ornamentation.
- 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_69d6aa895f4c8190887a15460ef622f4 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d771f5bef481909043656c571fda89 |
completed | April 9, 2026, 9:31 a.m. |
| PD | Predicate disambiguation | batch_69d72e9055908190b438f039574aaaaf |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:24 p.m.