Triple
T32230306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ellis Square (Savannah, Georgia) |
E823321
|
entity |
| Predicate | parkingGarageConstructed |
P3380
|
FINISHED |
| Object | 1950s |
—
|
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: 1950s | Statement: [Ellis Square (Savannah, Georgia), parkingGarageConstructed, 1950s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: parkingGarageConstructed Context triple: [Ellis Square (Savannah, Georgia), parkingGarageConstructed, 1950s]
-
A.
parkingStructure
Indicates that one entity is a parking facility or structure associated with another entity (such as a building, location, or organization).
-
B.
hasUndergroundParking
Indicates that a place or building provides parking facilities located below ground level.
-
C.
parkingType
chosen
Indicates the specific kind or category of parking arrangement associated with an entity (e.g., street, garage, lot, reserved).
-
D.
numberOfGarages
Indicates the quantity of garages associated with an entity (such as a property or building).
-
E.
numberOfParkingSpaces
Indicates the total count of parking spaces associated with a particular entity or location.
- 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_69f6bbfb18cc81908910b8609e74a0af |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6b632cf788190a3d0c08cd026b84b |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:39 a.m.