Triple
T573604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bering Sea |
E13715
|
entity |
| Predicate | locatedBetween |
P1262
|
FINISHED |
| Object | Alaska |
E890
|
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: Alaska | Statement: [Bering Sea, locatedBetween, Alaska]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alaska Context triple: [Bering Sea, locatedBetween, Alaska]
-
A.
Alaska
chosen
Alaska is the largest and one of the most sparsely populated U.S. states, known for its vast wilderness, Arctic and sub-Arctic climate, abundant natural resources, and rich Indigenous cultures.
-
B.
Hawaii
Hawaii is a U.S. state in the central Pacific Ocean known for its volcanic islands, tropical climate, and rich Native Hawaiian culture.
-
C.
Southcentral Alaska
Southcentral Alaska is a populous and relatively accessible region of Alaska known for its largest city, Anchorage, and its mix of coastal fjords, mountains, and boreal forests.
-
D.
Maine
Maine is a northeastern U.S. state known for its rugged coastline, maritime history, and vast forested interior.
-
E.
Maine
Maine is a historical region in northwestern France that played a significant role in the medieval power struggles between the English and French crowns.
- 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_69a4933fa4d88190a7949cc83c08c5c1 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49b4ae0988190bdd0ad428b784d85 |
completed | March 1, 2026, 8:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a5154fa9b48190be235b95548bbb94 |
completed | March 2, 2026, 4:42 a.m. |
Created at: March 1, 2026, 7:33 p.m.