Triple
T1671457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rouen Cathedral series |
E36133
|
entity |
| Predicate | colorFocus |
P31
|
FINISHED |
| Object | subtle color variations |
—
|
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: subtle color variations | Statement: [Rouen Cathedral series, colorFocus, subtle color variations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: colorFocus Context triple: [Rouen Cathedral series, colorFocus, subtle color variations]
-
A.
colors
Indicates that one entity assigns, describes, or provides the color or colors of another entity.
-
B.
focusesOn
chosen
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
C.
crestColor
Indicates the color characteristic of an entity’s crest.
-
D.
colorTheory
Indicates a relationship where principles or concepts about how colors interact, combine, or affect perception are applied or referenced between entities.
-
E.
colorCharge
Indicates a relationship where an entity possesses a specific quantum color charge (such as red, green, or blue) in the context of strong nuclear interactions.
- 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_69a8861286808190939afff3ce8ee31e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69ab272a653481908f48aa1eed5de8a4 |
completed | March 6, 2026, 7:12 p.m. |
| PD | Predicate disambiguation | batch_69aa61b2f6288190b2348ef7d7e4672d |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:29 p.m.