Triple
T22399411
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Custom House, Savannah, Georgia |
E553717
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Savannah |
—
|
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: Savannah | Statement: [U.S. Custom House, Savannah, Georgia, city, Savannah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Savannah Context triple: [U.S. Custom House, Savannah, Georgia, city, Savannah]
-
A.
Savannah
chosen
Savannah is a historic coastal city in the U.S. state of Georgia, renowned for its well-preserved architecture, cobblestone squares, and rich Southern cultural heritage.
-
B.
Savannah
Savannah is a residential district and one of the main suburban communities on Grand Cayman in the Cayman Islands.
-
C.
Savannah
Savannah is a feminine given name of Spanish origin meaning "treeless plain," commonly used in English-speaking countries.
-
D.
Savannah
Savannah is an American television drama series produced by Spelling Television that follows the intertwined lives and secrets of three young women in the Southern city of Savannah, Georgia.
-
E.
Savannah
Savannah is a free software hosting platform run by the GNU Project and the Free Software Foundation for managing and developing open-source projects.
- 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_69e11e4da7048190b4387d422a9a0de5 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f158b28e58819090624f131ce63a9f |
completed | April 29, 2026, 1:02 a.m. |
Created at: April 16, 2026, 8:46 p.m.