Triple
T24141453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fulton County, Kentucky |
E598243
|
entity |
| Predicate | isLocatedInSouthwesternTipOf |
P147508
|
FINISHED |
| Object | Kentucky |
—
|
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: Kentucky | Statement: [Fulton County, Kentucky, isLocatedInSouthwesternTipOf, Kentucky]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isLocatedInSouthwesternTipOf Context triple: [Fulton County, Kentucky, isLocatedInSouthwesternTipOf, Kentucky]
-
A.
isSouthernmostPartOf
Indicates that one entity is the geographically furthest south portion or section of another entity.
-
B.
locatedSouthWestOf
Indicates that one entity is positioned to the southwest of another entity, combining both a southern and western relative location.
-
C.
locatedInSouthwesternPartOf
chosen
Indicates that one entity is situated within the southwestern portion or region of another entity.
-
D.
locatedSouthOf
Indicates that one entity is positioned geographically to the south of another entity.
-
E.
southernmostCityOf
Indicates that one city is the geographically furthest south among all cities within a specified region or set.
- F. None of above.
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_69e288c92e448190ac57034fa0c863ce |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1e00737c08190af7c62d0aab30571 |
completed | April 29, 2026, 10:40 a.m. |
| PD | Predicate disambiguation | batch_69f1765650fc8190a6bc1eb512b240bf |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:28 p.m.