Triple
T2041500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexander Column |
E44754
|
entity |
| Predicate | angelDepicts |
P22304
|
FINISHED |
| Object | an angel holding a cross |
—
|
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: an angel holding a cross | Statement: [Alexander Column, angelDepicts, an angel holding a cross]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: angelDepicts Context triple: [Alexander Column, angelDepicts, an angel holding a cross]
-
A.
revelationAngel
Indicates that an angel is the one who delivers or mediates a divine revelation to someone or about something.
-
B.
oftenDepictedAs
Indicates that one entity is frequently represented or portrayed in the form, appearance, or symbolism of another entity.
-
C.
featuresAngel
chosen
Indicates that something includes or prominently presents an angel as a central element or subject.
-
D.
eraDepicted
Indicates that a work or representation portrays, illustrates, or is set in a particular historical era or time period.
-
E.
iconographicVariantOf
Indicates that one representation is an alternative visual or stylistic depiction of the same subject as another representation.
- 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_69a889159ec481908f9e4472d9f480c7 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abbc2c3f6c8190aff07097b2654e52 |
completed | March 7, 2026, 5:48 a.m. |
| PD | Predicate disambiguation | batch_69abb7aa00d4819086d347d9a08f81a0 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:39 p.m.