Triple
T64281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coat of arms of Belgium |
E1277
|
entity |
| Predicate | mantling |
P3351
|
FINISHED |
| Object | gules |
—
|
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: gules | Statement: [Coat of arms of Belgium, mantling, gules]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mantling Context triple: [Coat of arms of Belgium, mantling, gules]
-
A.
lays
Indicates that one entity deposits or places something, typically eggs or objects, onto a surface or in a location.
-
B.
backing
Indicates providing support, endorsement, or financial/resources assistance to someone or something, often enabling or strengthening their actions or position.
-
C.
decoration
chosen
Indicates that one entity serves as an ornament or embellishing element for another entity, enhancing its appearance or style.
-
D.
holding
Indicates that one entity is physically grasping, carrying, or keeping another entity in its possession or control.
-
E.
crownedWith
Indicates that one entity serves as a crown, top, or decorative upper covering placed upon another entity.
- 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_69a24ba4f760819081f6638a3c70538a |
completed | Feb. 28, 2026, 1:57 a.m. |
| NER | Named-entity recognition | batch_69a24fd16c248190a6ee4cd96c388772 |
completed | Feb. 28, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69a24ea3c44081908fa3856969881d1f |
completed | Feb. 28, 2026, 2:10 a.m. |
Created at: Feb. 28, 2026, 2:02 a.m.