Triple
T22531172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sfax, Georgia |
E557038
|
entity |
| Predicate | hasName |
P744
|
FINISHED |
| Object | Sfax, Georgia |
—
|
NE NERFINISHED |
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: Sfax, Georgia | Statement: [Sfax, Georgia, hasName, Sfax, Georgia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sfax, Georgia Context triple: [Sfax, Georgia, hasName, Sfax, Georgia]
-
A.
Sfax, Georgia (fictional example – ignore if inconsistent)
chosen
Sfax, Georgia is a fictional town in the U.S. state of Georgia, likely imagined as a namesake counterpart to the real city of Sfax in Tunisia.
-
B.
Cairo, Georgia
Cairo, Georgia is a small city in the southwestern part of the state known for its agricultural economy and historic downtown.
-
C.
Geneva, Georgia
Geneva, Georgia is a small rural town located in west-central Georgia in the United States.
-
D.
Sparta, Georgia
Sparta, Georgia is a small historic city in Hancock County known for its antebellum architecture and role as a rural county seat in central Georgia.
-
E.
Sari, Georgia
Sari, Georgia is a small, likely rural locality in the U.S. state of Georgia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ed6734881908abbbee477dfab98 |
completed | April 29, 2026, 1:28 a.m. |
Created at: April 16, 2026, 8:51 p.m.