Triple
T16322589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banksy’s Mild Mild West mural |
E396334
|
entity |
| Predicate | lightingDepiction |
P30545
|
FINISHED |
| Object | night-time scene |
—
|
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: night-time scene | Statement: [Banksy’s Mild Mild West mural, lightingDepiction, night-time scene]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lightingDepiction Context triple: [Banksy’s Mild Mild West mural, lightingDepiction, night-time scene]
-
A.
hasLighting
Indicates that one entity is equipped with, contains, or is characterized by a particular type or configuration of lighting.
-
B.
lightingCharacteristic
chosen
Indicates the specific qualities or properties of how something is lit, such as brightness, color, direction, or style of illumination.
-
C.
lightingColor
Indicates the color or hue of the lighting applied to or associated with an entity.
-
D.
lightingDependsOn
Indicates that the state or behavior of lighting is determined or influenced by another specified factor or condition.
-
E.
lightingRequirement
Indicates the level or type of light that is needed for something to function, grow, or be used properly.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e296b706108190b43a05b784633050 |
completed | April 17, 2026, 8:23 p.m. |
| PD | Predicate disambiguation | batch_69e219fc72c881909d452274e7af8238 |
completed | April 17, 2026, 11:31 a.m. |
Created at: April 10, 2026, 5:06 a.m.