Triple
T8455696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UMFK |
E199913
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Fort Kent |
E6034
|
NE 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: Fort Kent | Statement: [UMFK, city, Fort Kent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fort Kent Context triple: [UMFK, city, Fort Kent]
-
A.
Fort Kent, Maine
chosen
Fort Kent, Maine is a small town in northern Aroostook County known for its location at the Canadian border and as a gateway to the North Maine Woods.
-
B.
Athol
Athol is a small rural community in northern Idaho, United States, known as a gateway to nearby lakes, forests, and outdoor recreation areas.
-
C.
Castleton, Vermont
Castleton, Vermont is a small historic town in western Vermont known for Castleton University and its location near Lake Bomoseen.
-
D.
Airmont
Airmont is Intel’s low-power CPU microarchitecture designed as an energy-efficient evolution of its Atom line, primarily used in mobile and compact computing devices.
-
E.
Mapleton
Mapleton is a small village in Derbyshire, England, known for its picturesque rural setting in the Peak District near the River Dove.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8318231881908fd1bc1c4d45d286 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe48e0ae481908b40f7f124b0551e |
completed | March 31, 2026, 3:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cef2fa85ac8190adb7ddeb672bc550 |
completed | April 2, 2026, 10:51 p.m. |
Created at: March 30, 2026, 6:10 p.m.