Triple
T34416925
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Dome |
E883422
|
entity |
| Predicate | relativeToBuilding |
P59923
|
FINISHED |
| Object | crowns the main crossing of the basilica |
—
|
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: crowns the main crossing of the basilica | Statement: [Great Dome, relativeToBuilding, crowns the main crossing of the basilica]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeToBuilding Context triple: [Great Dome, relativeToBuilding, crowns the main crossing of the basilica]
-
A.
positionRelativeToBuilding
chosen
Indicates the spatial relationship of an entity’s location with respect to a specific building (e.g., in front of, behind, adjacent to, on top of).
-
B.
refersToBuildingOn
Indicates that one entity explicitly references or designates a specific building as its subject or target.
-
C.
attachedBuilding
Indicates that one building is physically connected to or joined with another building as part of the same structural complex.
-
D.
locatedInSectionOfBuilding
Indicates that one entity is situated within a specific section or area of a building.
-
E.
locatedOnBuilding
Indicates that one entity is physically situated on the exterior or rooftop surface of a building.
- 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_69f349c2e3b88190a67834eb5bcffeaf |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379fbe4a08190bfe65ebd141164e9 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:59 a.m.