Triple
T28114698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arc de Triomphe du Carrousel |
E710587
|
entity |
| Predicate | originalQuadrigaSource |
P197050
|
FINISHED |
| Object | Horses of Saint Mark |
—
|
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: Horses of Saint Mark | Statement: [Arc de Triomphe du Carrousel, originalQuadrigaSource, Horses of Saint Mark]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalQuadrigaSource Context triple: [Arc de Triomphe du Carrousel, originalQuadrigaSource, Horses of Saint Mark]
-
A.
originOfEngine
Indicates the source or place from which an engine originates or is produced.
-
B.
describesOriginOf
Indicates that one entity specifies or explains the source, provenance, or origin of another entity.
-
C.
previousRollingStockOrigin
Indicates that one entity is the place or source from which the immediately preceding piece of rolling stock (e.g., train car or unit) originated.
-
D.
machineOrigin
Indicates that one entity is the source, creator, or place of manufacture for a machine-related entity.
-
E.
McuOrigin
Indicates that one entity is the original source or first appearance of a Marvel Cinematic Universe (MCU) character, concept, or element.
- F. None of above. chosen
Provenance (4 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_69ef9b72f63081909dfbc2c1ddae86c6 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69fe766490c081908c49c8cc07d0ae9b |
completed | May 8, 2026, 11:48 p.m. |
| PD | Predicate disambiguation | batch_69fe75bb5f4481908572a5ffcbdc5154 |
completed | May 8, 2026, 11:46 p.m. |
| PDg | Predicate description generation | batch_69fe7663b5bc81909524c40d3a172512 |
completed | May 8, 2026, 11:48 p.m. |
Created at: April 27, 2026, 9:13 p.m.