Triple
T350245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tennessee (eastern portion) |
E7424
|
entity |
| Predicate | hasNationalForest |
P11107
|
FINISHED |
| Object |
Cherokee National Forest
Cherokee National Forest is a large federally managed woodland area in eastern Tennessee known for its Appalachian Mountain landscapes, diverse wildlife, and extensive outdoor recreation opportunities.
|
E59777
|
NE FINISHED |
How this triple was built (5 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: Cherokee National Forest | Statement: [Tennessee (eastern portion), hasNationalForest, Cherokee National Forest]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cherokee National Forest Context triple: [Tennessee (eastern portion), hasNationalForest, Cherokee National Forest]
-
A.
Apalachicola National Forest
Apalachicola National Forest is a large protected woodland in the Florida Panhandle known for its longleaf pine ecosystems, diverse wildlife, and extensive hiking and recreation opportunities.
-
B.
Great Smoky Mountains National Park
Great Smoky Mountains National Park is a vast, biodiverse preserve in the Appalachian Mountains renowned for its mist-covered peaks, rich wildlife, and status as one of the most visited national parks in the United States.
-
C.
Stanislaus National Forest
Stanislaus National Forest is a large, federally managed forest in California known for its rugged Sierra Nevada landscapes, extensive recreation opportunities, and diverse wildlife habitats.
-
D.
Ha-De-Ron-Dah Wilderness Area
Ha-De-Ron-Dah Wilderness Area is a remote, forested wilderness preserve in New York’s Adirondack Park known for its rugged terrain, wetlands, and backcountry recreation opportunities.
-
E.
Santa Fe National Forest
Santa Fe National Forest is a large protected area in northern New Mexico known for its diverse mountain landscapes, forests, and extensive recreational opportunities such as hiking, camping, and skiing.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cherokee National Forest Triple: [Tennessee (eastern portion), hasNationalForest, Cherokee National Forest]
Generated description
Cherokee National Forest is a large federally managed woodland area in eastern Tennessee known for its Appalachian Mountain landscapes, diverse wildlife, and extensive outdoor recreation opportunities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Cherokee National Forest Target entity description: Cherokee National Forest is a large federally managed woodland area in eastern Tennessee known for its Appalachian Mountain landscapes, diverse wildlife, and extensive outdoor recreation opportunities.
-
A.
Apalachicola National Forest
Apalachicola National Forest is a large protected woodland in the Florida Panhandle known for its longleaf pine ecosystems, diverse wildlife, and extensive hiking and recreation opportunities.
-
B.
Great Smoky Mountains National Park
Great Smoky Mountains National Park is a vast, biodiverse preserve in the Appalachian Mountains renowned for its mist-covered peaks, rich wildlife, and status as one of the most visited national parks in the United States.
-
C.
Stanislaus National Forest
Stanislaus National Forest is a large, federally managed forest in California known for its rugged Sierra Nevada landscapes, extensive recreation opportunities, and diverse wildlife habitats.
-
D.
Ha-De-Ron-Dah Wilderness Area
Ha-De-Ron-Dah Wilderness Area is a remote, forested wilderness preserve in New York’s Adirondack Park known for its rugged terrain, wetlands, and backcountry recreation opportunities.
-
E.
Santa Fe National Forest
Santa Fe National Forest is a large protected area in northern New Mexico known for its diverse mountain landscapes, forests, and extensive recreational opportunities such as hiking, camping, and skiing.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNationalForest Context triple: [Tennessee (eastern portion), hasNationalForest, Cherokee National Forest]
-
A.
hasMajorForest
Indicates that an entity possesses or contains a large, significant forested area.
-
B.
nationalPark
Indicates that a location is designated and managed as a national park by a governing authority.
-
C.
hasNationalSeashore
Indicates that a place or region is designated and managed as a national seashore.
-
D.
withinNationalPark
Indicates that one entity is located inside the geographic boundaries of a national park designated by another entity.
-
E.
hasNotableNationalPark
Indicates that a place or region contains or is associated with a nationally recognized park of particular significance.
- F. None of above. chosen
Provenance (7 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_69a2e7e696948190bebc966535995e45 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eb1f028c819098fa6480b4ca5cf0 |
completed | Feb. 28, 2026, 1:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a467f9e87481909e59ee41f558689c |
completed | March 1, 2026, 4:23 p.m. |
| NEDg | Description generation | batch_69a46a2e93f4819081b5e2e9f1beca71 |
completed | March 1, 2026, 4:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a46a8c557881908458fe67f319e90a |
completed | March 1, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69a2e955d1f88190bd687c46fa7c5469 |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea60e590819081779a6510918d9b |
completed | Feb. 28, 2026, 1:15 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.