Triple
T5223605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Mark's Basilica |
E117929
|
entity |
| Predicate | floorDecoration |
P14640
|
FINISHED |
| Object | opus sectile marble pavement |
—
|
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: opus sectile marble pavement | Statement: [St Mark's Basilica, floorDecoration, opus sectile marble pavement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floorDecoration Context triple: [St Mark's Basilica, floorDecoration, opus sectile marble pavement]
-
A.
floorCharacteristic
Indicates that a specified characteristic or property is attributed to a floor or flooring surface.
-
B.
floorConfiguration
Indicates how the layout, structure, or arrangement of floors or levels is organized or configured in relation to one another.
-
C.
floorType
chosen
Indicates the type or material classification of a floor associated with an entity.
-
D.
floor
Indicates that one entity is located on or forms the walking surface (the floor) beneath another entity within a space.
-
E.
interiorFloor
Indicates that one entity is the interior floor surface or flooring of another enclosing space or structure.
- 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_69bd4465e03081909bfcfd7113062590 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7abd3ed48190bfd8d2f2ca399741 |
completed | March 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69bd77bd2a448190a9ae5afd2585a7b9 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:48 p.m.