Triple
T21369233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marias River |
E527006
|
entity |
| Predicate | formsReservoir |
P11309
|
FINISHED |
| Object |
Lake Elwell
Lake Elwell is a man-made reservoir in north-central Montana, primarily used for irrigation, recreation, and flood control.
|
E1579261
|
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: Lake Elwell | Statement: [Marias River, formsReservoir, Lake Elwell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lake Elwell Context triple: [Marias River, formsReservoir, Lake Elwell]
-
A.
Lake Wilcox
Lake Wilcox is a kettle lake in Richmond Hill, Ontario, known as a popular local spot for recreation, nature viewing, and waterfront parks.
-
B.
Lake Greeson
Lake Greeson is a man-made reservoir in southwest Arkansas known for fishing, boating, and outdoor recreation.
-
C.
Lake Merwin
Lake Merwin is a large reservoir on the Lewis River in southwestern Washington State, popular for boating, fishing, and other outdoor recreation.
-
D.
Lake Wyola
Lake Wyola is a scenic freshwater lake in Shutesbury, Massachusetts, popular for swimming, boating, and outdoor recreation.
-
E.
Lake Wylie
Lake Wylie is a man-made reservoir on the Catawba River along the North Carolina–South Carolina border, popular for boating, fishing, and lakeside residential communities.
- 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: Lake Elwell Triple: [Marias River, formsReservoir, Lake Elwell]
Generated description
Lake Elwell is a man-made reservoir in north-central Montana, primarily used for irrigation, recreation, and flood control.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lake Elwell Target entity description: Lake Elwell is a man-made reservoir in north-central Montana, primarily used for irrigation, recreation, and flood control.
-
A.
Lake Wilcox
Lake Wilcox is a kettle lake in Richmond Hill, Ontario, known as a popular local spot for recreation, nature viewing, and waterfront parks.
-
B.
Lake Greeson
Lake Greeson is a man-made reservoir in southwest Arkansas known for fishing, boating, and outdoor recreation.
-
C.
Lake Merwin
Lake Merwin is a large reservoir on the Lewis River in southwestern Washington State, popular for boating, fishing, and other outdoor recreation.
-
D.
Lake Wyola
Lake Wyola is a scenic freshwater lake in Shutesbury, Massachusetts, popular for swimming, boating, and outdoor recreation.
-
E.
Lake Wylie
Lake Wylie is a man-made reservoir on the Catawba River along the North Carolina–South Carolina border, popular for boating, fishing, and lakeside residential communities.
- 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_69e0b51e80808190ba5cb05667af02a9 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b0ad04e081908ff02b2ee2bc7485 |
completed | April 22, 2026, 11:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c4c5c6c848190b9ebf0abf4a8435d |
completed | May 19, 2026, 11:41 a.m. |
| NEDg | Description generation | batch_6a0c4d2cb4848190b7a10e1184ca0064 |
completed | May 19, 2026, 11:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c4daeaf5c81909eca82f6d9103b9a |
completed | May 19, 2026, 11:46 a.m. |
Created at: April 16, 2026, 5:09 p.m.