Triple
T16375833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chefchaouen |
E397676
|
entity |
| Predicate | streetColorTradition |
P31069
|
FINISHED |
| Object | blue-washed walls |
—
|
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: blue-washed walls | Statement: [Chefchaouen, streetColorTradition, blue-washed walls]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: streetColorTradition Context triple: [Chefchaouen, streetColorTradition, blue-washed walls]
-
A.
hasTraditionalColors
chosen
Indicates that an entity is associated with colors that are traditionally or customarily linked to it.
-
B.
roadUniformColor
Indicates that the entire road surface shares a single, consistent color throughout.
-
C.
traditionalHomeColor
Indicates the customary or historically typical color associated with a home in a given cultural or regional tradition.
-
D.
roadUniformColorPrimary
Indicates that the primary uniform color associated with a road (e.g., for mapping or visualization) is a specified color.
-
E.
homeKitTraditionalColor
Indicates that an entity’s color is represented using the traditional HomeKit color model or palette.
- 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e319d79df8819087285b9457b7bdb6 |
completed | April 18, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69e226f94dd48190b7b8e0e983738a67 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:08 a.m.