Triple
T5155931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portrait of Madame d’Haussonville |
E116307
|
entity |
| Predicate | depictsInterior |
P1581
|
FINISHED |
| Object | elegant aristocratic room |
—
|
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: elegant aristocratic room | Statement: [Portrait of Madame d’Haussonville, depictsInterior, elegant aristocratic room]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictsInterior Context triple: [Portrait of Madame d’Haussonville, depictsInterior, elegant aristocratic room]
-
A.
hasInteriorFeature
Indicates that an entity contains or includes a specific feature within its interior space.
-
B.
interiorStyle
Indicates that one entity has a particular interior design style or aesthetic characterized by the other entity.
-
C.
depictsResidence
Indicates that one entity visually represents or portrays the place where another entity lives or resides.
-
D.
interiorFloor
Indicates that one entity is the interior floor surface or flooring of another enclosing space or structure.
-
E.
depicts
chosen
Indicates that one entity visually represents, portrays, or shows another entity.
- 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_69bd445d94788190b72e2cc563120995 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd79c1354c81908176703b4853c1a4 |
completed | March 20, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69bd77b0fbb88190851e2d7ae1bdcc09 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:44 p.m.