Triple
T8564133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Sakakawea |
E202762
|
entity |
| Predicate | state |
P87
|
FINISHED |
| Object | North Dakota |
E31933
|
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: North Dakota | Statement: [Lake Sakakawea, state, North Dakota]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: North Dakota Context triple: [Lake Sakakawea, state, North Dakota]
-
A.
North Dakota
chosen
North Dakota is a sparsely populated U.S. state known for its Great Plains landscapes, agricultural economy, and significant oil production from the Bakken formation.
-
B.
South Dakota
South Dakota is a largely rural U.S. state known for the Black Hills, Mount Rushmore, and its Native American heritage.
-
C.
Montana
Montana is a large, sparsely populated U.S. state in the northern Rocky Mountains known for its expansive wilderness, national parks like Glacier, and wide-open "Big Sky" landscapes.
-
D.
Montana
Montana was a former Swiss alpine resort municipality that later became part of the larger resort area of Crans-Montana in the canton of Valais.
-
E.
Nebraska
Nebraska is a 2013 black-and-white American road comedy-drama film directed by Alexander Payne that follows an aging man's quixotic journey to claim a supposed sweepstakes prize.
- 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_69ca8326e6c881908ff720d6abaebdc5 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe9d11274819099cc33a21a993a1f |
completed | March 31, 2026, 3:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf9ffe17e481908516d2f526d60684 |
completed | April 3, 2026, 11:09 a.m. |
Created at: March 30, 2026, 6:20 p.m.