Triple
T28072566
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Santa Sabina |
E709445
|
entity |
| Predicate | originalMosaicApse |
P20183
|
FINISHED |
| Object | lost |
—
|
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: lost | Statement: [Santa Sabina, originalMosaicApse, lost]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalMosaicApse Context triple: [Santa Sabina, originalMosaicApse, lost]
-
A.
mosaicCreator
Indicates that an entity is the artist or maker responsible for creating a particular mosaic.
-
B.
mosaicTheme
Indicates that one entity has a thematic subject or motif that is depicted or expressed in a mosaic associated with it.
-
C.
mosaicLayout
Indicates that elements are arranged in a mosaic-style layout, typically combining varied sizes or shapes into a cohesive visual grid or pattern.
-
D.
mosaicMaterial
Indicates that something is made of, or incorporates, a specified material in its mosaic construction.
-
E.
originalAspect
chosen
Indicates that one entity represents the initial or primary form, version, or facet from which another related entity is derived or viewed as a variation.
- 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_69ef9b6f8078819098b741274cd1a2ee |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69fe72dca2f08190beff17de3d2aada6 |
completed | May 8, 2026, 11:33 p.m. |
| PD | Predicate disambiguation | batch_69fe70bca8d08190b810e1e616ceac44 |
completed | May 8, 2026, 11:24 p.m. |
Created at: April 27, 2026, 8:47 p.m.