Triple
T10257310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dublin, Georgia |
E240504
|
entity |
| Predicate | distanceToSavannah |
P93094
|
FINISHED |
| Object | about 120 miles west of Savannah |
—
|
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: about 120 miles west of Savannah | Statement: [Dublin, Georgia, distanceToSavannah, about 120 miles west of Savannah]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceToSavannah Context triple: [Dublin, Georgia, distanceToSavannah, about 120 miles west of Savannah]
-
A.
distanceToAtlanta
Indicates the measured or calculated distance between a given location and the city of Atlanta.
-
B.
directionFromSavannah
Indicates the cardinal or relative compass direction in which one entity is located from Savannah.
-
C.
distanceToFlorida
Indicates the spatial distance between a given entity’s location and the state of Florida.
-
D.
distanceToJackson
Indicates the spatial distance or separation between a given entity and Jackson.
-
E.
distanceToTopeka
Indicates the spatial distance between a given entity’s location and the city of Topeka.
- F. None of above. chosen
Provenance (4 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_69d381a7e198819090280d5ab885d59e |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2b5853081909cd0397e08a0f44d |
completed | April 7, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69d4d1edae6881909a65201b8e51ea0a |
completed | April 7, 2026, 9:44 a.m. |
| PDg | Predicate description generation | batch_69d4d2b4ae548190b4a4c671f86b82d1 |
completed | April 7, 2026, 9:47 a.m. |
Created at: April 6, 2026, 11:31 a.m.