Triple
T8570413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sant’Andrea, Mantua |
E202911
|
entity |
| Predicate | hasSideSpaces |
P77763
|
FINISHED |
| Object | sequence of side chapels |
—
|
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: sequence of side chapels | Statement: [Sant’Andrea, Mantua, hasSideSpaces, sequence of side chapels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSideSpaces Context triple: [Sant’Andrea, Mantua, hasSideSpaces, sequence of side chapels]
-
A.
isWrittenWithSpace
Indicates that something is written or represented with spaces separating its components or elements.
-
B.
hasSecondarySpace
chosen
Indicates that an entity possesses or is associated with an additional, subordinate, or auxiliary space beyond its primary one.
-
C.
hasSpaceType
Indicates that one entity is associated with, or classified by, a particular type or category of space.
-
D.
hasCodeSpaceSize
Indicates the size or capacity of the code space associated with an entity, such as the range or number of distinct codes it can represent.
-
E.
hasLanguageOnSides
Indicates that an object or medium features written or spoken language present on multiple sides or surfaces.
- 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_69ca8327b0a881908606ff860713964d |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbea4091f48190b5174d7a5cfd2bd8 |
completed | March 31, 2026, 3:37 p.m. |
| PD | Predicate disambiguation | batch_69cbd11856048190a1ce4b83a38f6965 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:21 p.m.