Triple
T19499766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Decatur, Georgia |
E487870
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Decatur Square |
E839629
|
NE 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: Decatur Square | Statement: [Decatur, Georgia, hasLandmark, Decatur Square]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Decatur Square Context triple: [Decatur, Georgia, hasLandmark, Decatur Square]
-
A.
Decatur Square
chosen
Decatur Square is the historic central plaza and social hub of downtown Decatur, Georgia, known for its restaurants, shops, public events, and community gatherings.
-
B.
Crawford Square
Crawford Square is one of Savannah, Georgia’s historic public squares, known for its preserved 19th-century character and role in the city’s distinctive urban plan.
-
C.
World Square
World Square is a themed area within the Window of the World park in Shenzhen, China, featuring iconic global landmarks and cultural displays in miniature form.
-
D.
World Square
World Square is a large mixed-use retail, dining, and commercial complex in central Sydney, Australia.
-
E.
Marietta Square
Marietta Square is a historic downtown park and commercial district in Marietta, Georgia, known for its shops, restaurants, events, and community gatherings.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8e8d9d1c88190b01cd78b8be49384 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6349462108190bb763b4e03bf000d |
completed | April 20, 2026, 2:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0747199f608190ad16737c7a49a089 |
completed | May 15, 2026, 4:17 p.m. |
Created at: April 10, 2026, 1:40 p.m.