Triple
T20198147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phelps Park (Decorah) |
E493141
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Downtown Decorah |
—
|
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: Downtown Decorah | Statement: [Phelps Park (Decorah), near, Downtown Decorah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Downtown Decorah Context triple: [Phelps Park (Decorah), near, Downtown Decorah]
-
A.
Decorah, Iowa
Decorah, Iowa is a small city in northeastern Iowa known for its Norwegian-American heritage, scenic bluffs and trout streams, and as the home of Luther College.
-
B.
Corydon, Iowa
Corydon, Iowa is a small rural city that serves as the county seat of Wayne County in southern Iowa.
-
C.
DeWitt, Iowa
DeWitt, Iowa is a small city in eastern Iowa known as a local commercial and residential hub within Clinton County.
-
D.
Decorah
chosen
Decorah is a small city in northeastern Iowa known for its scenic bluffs, Norwegian-American heritage, and as the home of Luther College.
-
E.
Elkader, Iowa
Elkader, Iowa is a small historic city in Clayton County known for its scenic location along the Turkey River and its unique namesake honoring Algerian leader Emir Abdelkader.
- 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_69da6269614c8190bb40475d9d477358 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66d8afe408190a7a9202ed67698e6 |
completed | April 20, 2026, 6:16 p.m. |
Created at: April 11, 2026, 11:37 p.m.