Triple
T32235162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MART |
E823446
|
entity |
| Predicate | hasMainBuildingFeature |
P6684
|
FINISHED |
| Object | large circular piazza with glass dome |
—
|
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: large circular piazza with glass dome | Statement: [MART, hasMainBuildingFeature, large circular piazza with glass dome]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainBuildingFeature Context triple: [MART, hasMainBuildingFeature, large circular piazza with glass dome]
-
A.
hasMainBuildings
Indicates that one entity possesses or is associated with one or more primary or principal buildings.
-
B.
hasMainEdifice
Indicates that an entity possesses or is associated with a primary or principal building or structure.
-
C.
hasArchitecturalFeature
chosen
Indicates that one entity possesses, includes, or is characterized by a specific architectural feature or element.
-
D.
hasMainHallType
Indicates the specific category or kind of main hall associated with an entity.
-
E.
hasMainHall
Indicates that an entity possesses or includes a primary or central hall as a significant internal space.
- 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_69f3490c140481908ed53b98b561eaa1 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a008098e5dc8190b7ccad8bab780343 |
completed | May 10, 2026, 12:56 p.m. |
| PD | Predicate disambiguation | batch_6a008037267c8190990225a6ff0b3694 |
completed | May 10, 2026, 12:55 p.m. |
Created at: May 1, 2026, 12:39 a.m.