Triple
T26225348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canadian coat of arms |
E655873
|
entity |
| Predicate | crestCrown |
P39797
|
FINISHED |
| Object | St Edward's Crown |
—
|
NE NERFINISHED |
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: St Edward's Crown | Statement: [Canadian coat of arms, crestCrown, St Edward's Crown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crestCrown Context triple: [Canadian coat of arms, crestCrown, St Edward's Crown]
-
A.
crownedWith
Indicates that one entity serves as a crown, top, or decorative upper covering placed upon another entity.
-
B.
crestElement
chosen
Indicates that one entity is a crest or emblematic design element associated with, or forming part of, another entity.
-
C.
crownDepicted
Indicates that one entity visually represents or shows a crown associated with another entity.
-
D.
crest
Indicates reaching the highest point or peak of something, such as a wave, hill, or trend, before it begins to decline.
-
E.
crownCharacteristic
Indicates that an entity has a particular property, feature, or quality specifically associated with its crown.
- 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_69ee5b4a77e08190bfcb5f8ecdc55abd |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f60d52e1e4819095c8efd797107332 |
completed | May 2, 2026, 2:42 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fd90fc81909055b211368f9139 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 8:57 p.m.