Triple
T3994347
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jackson County, Michigan |
E87063
|
entity |
| Predicate | hasLake |
P1025
|
FINISHED |
| Object |
Clark Lake
Clark Lake is a recreational inland lake in Jackson County, Michigan, known for boating, fishing, and lakeside cottages.
|
E692040
|
NE FINISHED |
How this triple was built (4 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: Clark Lake | Statement: [Jackson County, Michigan, hasLake, Clark Lake]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Clark Lake Context triple: [Jackson County, Michigan, hasLake, Clark Lake]
-
A.
Wood Lake
Wood Lake is a freshwater lake in British Columbia’s Okanagan region, known for recreation, fishing, and its role in the local valley ecosystem.
-
B.
Castle Lake
Castle Lake is the scenic body of water in Hillerød, Denmark, that forms the picturesque setting around the historic Frederiksborg Castle.
-
C.
Castle Lake
Castle Lake is a high-altitude alpine lake nestled within Nevada’s Ruby Mountains, known for its rugged scenic surroundings and remote, pristine setting.
-
D.
June Lake
June Lake is a scenic alpine lake and resort community in California’s Eastern Sierra Nevada, known for fishing, hiking, and skiing.
-
E.
Jefferson Lake
Jefferson Lake is a scenic body of water located within Forest Park in St. Louis, Missouri, popular for its tranquil views and surrounding green space.
- 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: Clark Lake Triple: [Jackson County, Michigan, hasLake, Clark Lake]
Generated description
Clark Lake is a recreational inland lake in Jackson County, Michigan, known for boating, fishing, and lakeside cottages.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Clark Lake Target entity description: Clark Lake is a recreational inland lake in Jackson County, Michigan, known for boating, fishing, and lakeside cottages.
-
A.
Wood Lake
Wood Lake is a freshwater lake in British Columbia’s Okanagan region, known for recreation, fishing, and its role in the local valley ecosystem.
-
B.
Castle Lake
Castle Lake is the scenic body of water in Hillerød, Denmark, that forms the picturesque setting around the historic Frederiksborg Castle.
-
C.
Castle Lake
Castle Lake is a high-altitude alpine lake nestled within Nevada’s Ruby Mountains, known for its rugged scenic surroundings and remote, pristine setting.
-
D.
June Lake
June Lake is a scenic alpine lake and resort community in California’s Eastern Sierra Nevada, known for fishing, hiking, and skiing.
-
E.
Jefferson Lake
Jefferson Lake is a scenic body of water located within Forest Park in St. Louis, Missouri, popular for its tranquil views and surrounding green space.
- F. None of above. chosen
Provenance (5 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_69aed94118148190975e6aa4e554cde9 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefa1f0fb88190aafbfdc98bc8652d |
completed | March 9, 2026, 4:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c9d13a8b108190a0b13592f3a6362e |
completed | March 30, 2026, 1:26 a.m. |
| NEDg | Description generation | batch_69c9d44d0d2881909f4ed7af19ae5f02 |
completed | March 30, 2026, 1:39 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c9d4cab81081908c374a250e9f3fa2 |
completed | March 30, 2026, 1:41 a.m. |
Created at: March 9, 2026, 3:34 p.m.