Triple
T3629404
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akan-Mashu National Park |
E76918
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Lake Akan
Lake Akan is a scenic caldera lake in eastern Hokkaido, Japan, famed for its rare marimo (spherical green algae) and hot spring resort surroundings.
|
E380966
|
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 Akan | Statement: [Akan-Mashu National Park, hasPart, Lake Akan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lake Akan Context triple: [Akan-Mashu National Park, hasPart, Lake Akan]
-
A.
Lake Shikotsu
Lake Shikotsu is a deep caldera lake in Hokkaido, Japan, renowned for its exceptionally clear water and scenic volcanic surroundings.
-
B.
Lake Inari
Lake Inari is a large Arctic lake in northern Finland, renowned for its rugged natural beauty and cultural significance to the Indigenous Sámi people.
-
C.
Lake Shikaribetsu
Lake Shikaribetsu is a scenic mountain lake in central Hokkaido, Japan, known for its clear waters, surrounding forested peaks, and seasonal ice village attractions.
-
D.
Lake Kakumanbuchi
Lake Kakumanbuchi is a small crater lake situated on the volcanic Mount Akagi in Gunma Prefecture, Japan.
-
E.
Lake Shoji
Lake Shoji is one of the Fuji Five Lakes in Japan, known for its tranquil waters and scenic views of Mount Fuji.
- 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 Akan Triple: [Akan-Mashu National Park, hasPart, Lake Akan]
Generated description
Lake Akan is a scenic caldera lake in eastern Hokkaido, Japan, famed for its rare marimo (spherical green algae) and hot spring resort surroundings.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lake Akan Target entity description: Lake Akan is a scenic caldera lake in eastern Hokkaido, Japan, famed for its rare marimo (spherical green algae) and hot spring resort surroundings.
-
A.
Lake Shikotsu
Lake Shikotsu is a deep caldera lake in Hokkaido, Japan, renowned for its exceptionally clear water and scenic volcanic surroundings.
-
B.
Lake Inari
Lake Inari is a large Arctic lake in northern Finland, renowned for its rugged natural beauty and cultural significance to the Indigenous Sámi people.
-
C.
Lake Shikaribetsu
Lake Shikaribetsu is a scenic mountain lake in central Hokkaido, Japan, known for its clear waters, surrounding forested peaks, and seasonal ice village attractions.
-
D.
Lake Kakumanbuchi
Lake Kakumanbuchi is a small crater lake situated on the volcanic Mount Akagi in Gunma Prefecture, Japan.
-
E.
Lake Shoji
Lake Shoji is one of the Fuji Five Lakes in Japan, known for its tranquil waters and scenic views of Mount Fuji.
- 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_69ad85dc03948190b35b7189e4175bcc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc300223881909019982ebf194f78 |
completed | March 8, 2026, 6:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4c3852e60819092db2992e945a4c7 |
completed | March 14, 2026, 2:10 a.m. |
| NEDg | Description generation | batch_69b4c7f0fe1c8190b66e3fcecfae3f6e |
completed | March 14, 2026, 2:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4c840713c81908e3d565d663e04d5 |
completed | March 14, 2026, 2:30 a.m. |
Created at: March 8, 2026, 3:23 p.m.