Triple
T32368053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lion of Brunswick |
E827049
|
entity |
| Predicate | heraldicCategory |
P32838
|
FINISHED |
| Object | beast |
—
|
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: beast | Statement: [Lion of Brunswick, heraldicCategory, beast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heraldicCategory Context triple: [Lion of Brunswick, heraldicCategory, beast]
-
A.
heraldicAspect
Indicates a relationship where one entity serves as a heraldic feature, attribute, or component in the coat of arms or heraldic representation of another entity.
-
B.
heraldicStatus
Indicates the formal standing or classification of an entity within a heraldic system, such as its rank, legitimacy, or official recognition in heraldry.
-
C.
coatOfArms
Indicates that one entity serves as the heraldic emblem or coat of arms representing another entity.
-
D.
heraldicConnection
Indicates a relationship where entities are linked through heraldry, such as by shared coats of arms, heraldic symbols, lineage, or official armorial associations.
-
E.
heraldicCharge
chosen
Indicates that one entity serves as a heraldic charge, i.e., a symbolic figure or emblem placed on another entity’s coat of arms or shield.
- 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_69f349166d548190887b412fe908e2f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6be9f57048190819d133d4caba58e |
completed | May 3, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6eb32c8190bf405b2011fa48f7 |
completed | May 3, 2026, 3:01 a.m. |
Created at: May 1, 2026, 12:50 a.m.