Triple
T1697491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rouen Cathedral |
E36690
|
entity |
| Predicate | paintingSeriesDepicts |
P20066
|
FINISHED |
| Object | cathedral in different lights and seasons |
—
|
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: cathedral in different lights and seasons | Statement: [Rouen Cathedral, paintingSeriesDepicts, cathedral in different lights and seasons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paintingSeriesDepicts Context triple: [Rouen Cathedral, paintingSeriesDepicts, cathedral in different lights and seasons]
-
A.
artisticDepiction
chosen
Indicates that one entity visually represents, portrays, or illustrates another in an artistic medium.
-
B.
placeOfDepiction
Indicates the location or setting where the depicted subject is shown as being situated in the representation.
-
C.
depictionDetail
Indicates that one depiction provides additional detail, refinement, or a closer view of what is shown in another depiction.
-
D.
numberOfFiguresDepicted
Indicates the total count of distinct figures shown within a given depiction or representation.
-
E.
coverArtDepicts
Indicates that the subject cover art visually represents, portrays, or includes the object within its imagery.
- 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_69a886163dec8190859c514232a37a05 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aaf169da888190b3aa334752f1952b |
completed | March 6, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69aa61b8ce348190b46154af0b041ff0 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:30 p.m.