Triple
T10723674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winged lion |
E252883
|
entity |
| Predicate | oneOfSymbolsOf |
P129
|
FINISHED |
| Object | four Evangelists |
—
|
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: four Evangelists | Statement: [Winged lion, oneOfSymbolsOf, four Evangelists]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oneOfSymbolsOf Context triple: [Winged lion, oneOfSymbolsOf, four Evangelists]
-
A.
symbolizedIn
Indicates that one entity serves as a symbol or representation of another entity.
-
B.
typicalSymbol
Indicates that something serves as a characteristic or commonly recognized symbol representing something else.
-
C.
appearsWithSymbol
Indicates that one entity is shown or presented together with a particular symbol in the same visual or contextual setting.
-
D.
knownAsOneOf
Indicates that an entity is recognized or referred to as one member of a specified set of alternative names, labels, or identities.
-
E.
symbolizes
chosen
Indicates that one entity stands for, represents, or is used as a sign for another entity, concept, or idea.
- 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_69d6aa5d8be481909a43218b2bfdbe95 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d70d46234081908e147638d0cb7e22 |
completed | April 9, 2026, 2:21 a.m. |
| PD | Predicate disambiguation | batch_69d6f30455888190b77f476b8418eaee |
completed | April 9, 2026, 12:29 a.m. |
Created at: April 8, 2026, 9:14 p.m.