Triple
T10017160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hida Mountains |
E199523
|
entity |
| Predicate | containsPeak |
P8205
|
FINISHED |
| Object |
Mount Kasa
Mount Kasa is a prominent peak in Japan’s Northern Alps, known for its distinctive triangular shape and popular hiking routes.
|
E849719
|
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 Kasa | Statement: [Hida Mountains, containsPeak, Mount Kasa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Kasa Context triple: [Hida Mountains, containsPeak, Mount Kasa]
-
A.
Mount Terevaka
Mount Terevaka is the highest and youngest of the three main volcanoes forming Easter Island (Rapa Nui) in the southeastern Pacific Ocean.
-
B.
Mount Kotilion
Mount Kotilion is a mountain in the Peloponnese region of Greece known for the ancient sanctuary and temple dedicated to Apollo Epicurius at its slopes.
-
C.
Mount Kawi
Mount Kawi is a stratovolcano in East Java, Indonesia, known for its scenic highland landscapes and cultural significance to local communities.
-
D.
Mount Muna
Mount Muna is the highest peak on Alor Island in Indonesia, known as a prominent landmark in the island’s rugged volcanic landscape.
-
E.
Mount Rizeh
Mount Rizeh is the tallest peak in the Kopet Dag mountain range along the border of Iran and Turkmenistan.
- 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 Kasa Triple: [Hida Mountains, containsPeak, Mount Kasa]
Generated description
Mount Kasa is a prominent peak in Japan’s Northern Alps, known for its distinctive triangular shape and popular hiking routes.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mount Kasa Target entity description: Mount Kasa is a prominent peak in Japan’s Northern Alps, known for its distinctive triangular shape and popular hiking routes.
-
A.
Mount Terevaka
Mount Terevaka is the highest and youngest of the three main volcanoes forming Easter Island (Rapa Nui) in the southeastern Pacific Ocean.
-
B.
Mount Kotilion
Mount Kotilion is a mountain in the Peloponnese region of Greece known for the ancient sanctuary and temple dedicated to Apollo Epicurius at its slopes.
-
C.
Mount Kawi
Mount Kawi is a stratovolcano in East Java, Indonesia, known for its scenic highland landscapes and cultural significance to local communities.
-
D.
Mount Muna
Mount Muna is the highest peak on Alor Island in Indonesia, known as a prominent landmark in the island’s rugged volcanic landscape.
-
E.
Mount Rizeh
Mount Rizeh is the tallest peak in the Kopet Dag mountain range along the border of Iran and Turkmenistan.
- 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_69ca8315a1a08190ab310f25620f362b |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd4c17848190bf1a8017e755ba75 |
completed | April 2, 2026, 1:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6527343048190b3bb13b33c32fbf7 |
completed | April 8, 2026, 1:04 p.m. |
| NEDg | Description generation | batch_69d65377b1688190b776db55e40e72fb |
completed | April 8, 2026, 1:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d653f01c508190a9e1d674dc0c84fd |
completed | April 8, 2026, 1:11 p.m. |
Created at: March 30, 2026, 8:53 p.m.