Triple
T1036491
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terrell County, Georgia |
E22374
|
entity |
| Predicate | countySeat |
P383
|
FINISHED |
| Object | Dawson, Georgia |
E118552
|
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: Dawson, Georgia | Statement: [Terrell County, Georgia, countySeat, Dawson, Georgia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dawson, Georgia Context triple: [Terrell County, Georgia, countySeat, Dawson, Georgia]
-
A.
Dawson, Georgia
chosen
Dawson, Georgia is a small city in Terrell County known as an agricultural and regional trade center in southwest Georgia.
-
B.
Dahlonega, Georgia
Dahlonega, Georgia is a historic North Georgia mountain town best known as the site of one of the first major U.S. gold rushes and now a popular tourist destination with a preserved 19th-century downtown.
-
C.
Dalton, Georgia
Dalton, Georgia is a city in northwest Georgia known as a major center of the U.S. carpet and floor-covering industry.
-
D.
Woolsey, Georgia
Woolsey, Georgia is a small incorporated town located in Fayette County in the U.S. state of Georgia.
-
E.
Morrow, Georgia
Morrow, Georgia is a small suburban city in the Atlanta metropolitan area known for housing Clayton State University and various retail and commercial centers.
- 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_69a493d848848190aed4011b34b2e8d3 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b82a1014819085bfc077e24c9742 |
completed | March 1, 2026, 10:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad293450488190ac8a795524ca0c2c |
completed | March 8, 2026, 7:45 a.m. |
Created at: March 1, 2026, 7:41 p.m.