Triple
T3186112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Conversion of Saint Paul |
E66701
|
entity |
| Predicate | useOfLight |
P33064
|
FINISHED |
| Object | strong contrast of light and shadow |
—
|
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: strong contrast of light and shadow | Statement: [The Conversion of Saint Paul, useOfLight, strong contrast of light and shadow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: useOfLight Context triple: [The Conversion of Saint Paul, useOfLight, strong contrast of light and shadow]
-
A.
lightSourceFor
Indicates that one entity serves as the source of illumination for another entity.
-
B.
litOn
Indicates that one entity is illuminated or activated by a light source associated with another entity.
-
C.
lightPath
Indicates the route or trajectory that light follows as it travels between entities or through a medium.
-
D.
usesLightingFor
chosen
Indicates that one entity employs or relies on a particular lighting setup, technology, or condition to achieve a purpose or perform an action.
-
E.
lightSourceGeneration
Indicates that an entity produces or emits light, serving as a source of illumination for other entities or the environment.
- 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_69ad8587c1bc8190a2595f2c22ee1001 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada6c32ce88190a231be18d38ec5ba |
completed | March 8, 2026, 4:41 p.m. |
| PD | Predicate disambiguation | batch_69ad9e04290481909092ddfbe6fdaabc |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.