Triple
T8580573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hakodate |
E203163
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Mount Hakodate
Mount Hakodate is a scenic mountain in Hakodate, Japan, famous for its panoramic night views over the city and harbor.
|
E752777
|
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: Mount Hakodate | Statement: [Hakodate, hasLandmark, Mount Hakodate]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Hakodate Context triple: [Hakodate, hasLandmark, Mount Hakodate]
-
A.
Mount Hakusan
Mount Hakusan is one of Japan’s “Three Holy Mountains,” a prominent volcanic peak revered in Shinto and Buddhist traditions for its spiritual significance and natural beauty.
-
B.
Mount Furutaka
Mount Furutaka is a mountain in Japan notable enough to have lent its name to the Imperial Japanese Navy cruiser Furutaka.
-
C.
Minamidake
Minamidake is one of the principal active summit craters of the Sakurajima volcano in Kagoshima Prefecture, Japan.
-
D.
Mount Hakkoda
Mount Hakkoda is a volcanic mountain complex in northern Honshu, Japan, known for its heavy snowfall, scenic hiking, and tragic 1902 military snowstorm disaster.
-
E.
Mount Atago
Mount Atago is a prominent mountain in Japan, revered for its Shinto shrines and historical significance as a site dedicated to the fire deity Atago Gongen.
- 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: Mount Hakodate Triple: [Hakodate, hasLandmark, Mount Hakodate]
Generated description
Mount Hakodate is a scenic mountain in Hakodate, Japan, famous for its panoramic night views over the city and harbor.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mount Hakodate Target entity description: Mount Hakodate is a scenic mountain in Hakodate, Japan, famous for its panoramic night views over the city and harbor.
-
A.
Mount Hakusan
Mount Hakusan is one of Japan’s “Three Holy Mountains,” a prominent volcanic peak revered in Shinto and Buddhist traditions for its spiritual significance and natural beauty.
-
B.
Mount Furutaka
Mount Furutaka is a mountain in Japan notable enough to have lent its name to the Imperial Japanese Navy cruiser Furutaka.
-
C.
Minamidake
Minamidake is one of the principal active summit craters of the Sakurajima volcano in Kagoshima Prefecture, Japan.
-
D.
Mount Hakkoda
Mount Hakkoda is a volcanic mountain complex in northern Honshu, Japan, known for its heavy snowfall, scenic hiking, and tragic 1902 military snowstorm disaster.
-
E.
Mount Atago
Mount Atago is a prominent mountain in Japan, revered for its Shinto shrines and historical significance as a site dedicated to the fire deity Atago Gongen.
- 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_69ca8328ebe481909a8c038fa79959b4 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbeb1a026c819089183f542eeb7837 |
completed | March 31, 2026, 3:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf281edc348190a0c7e82dc4cb15c6 |
completed | April 3, 2026, 2:38 a.m. |
| NEDg | Description generation | batch_69cf2a6a91d48190aa7d45b0a010f261 |
completed | April 3, 2026, 2:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cf2c0aace08190aca839c39e718c52 |
completed | April 3, 2026, 2:55 a.m. |
Created at: March 30, 2026, 6:22 p.m.