Triple
T4926672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kashubians |
E110593
|
entity |
| Predicate | haveSymbol |
P30273
|
FINISHED |
| Object | Black griffin on yellow field |
—
|
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: Black griffin on yellow field | Statement: [Kashubians, haveSymbol, Black griffin on yellow field]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: haveSymbol Context triple: [Kashubians, haveSymbol, Black griffin on yellow field]
-
A.
hasSymbolNamedAfter
Indicates that one entity has a symbol whose name is derived from or dedicated to another entity.
-
B.
hasSymbolicValue
Indicates that something holds meaning, significance, or representational value beyond its literal or practical function.
-
C.
hasColorSymbol
Indicates that one entity is associated with another entity that serves as its representative or symbolic color.
-
D.
appearsWithSymbol
chosen
Indicates that one entity is shown or presented together with a particular symbol in the same visual or contextual setting.
-
E.
hasSymbolicForm
Indicates that one entity serves as the symbolic representation or abstract form of 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_69bd4415190c8190817bee7ec9f9f944 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd70354bd081909291a43439f42ed3 |
completed | March 20, 2026, 4:05 p.m. |
| PD | Predicate disambiguation | batch_69bd6c3695c8819094e7ad2f6d4ba1ac |
completed | March 20, 2026, 3:48 p.m. |
Created at: March 20, 2026, 1:30 p.m.