Triple
T19510111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ikoma Mountains |
E488126
|
entity |
| Predicate | hasHighestPoint |
P210
|
FINISHED |
| Object | Mount Ikoma |
—
|
NE NERFINISHED |
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: Mount Ikoma | Statement: [Ikoma Mountains, hasHighestPoint, Mount Ikoma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Ikoma Context triple: [Ikoma Mountains, hasHighestPoint, Mount Ikoma]
-
A.
Mount Ikoma
chosen
Mount Ikoma is a prominent mountain on the border of Osaka and Nara prefectures in Japan, known for its scenic views, temples, and popular hiking and leisure facilities.
-
B.
Mount Kumotori
Mount Kumotori is a prominent mountain on the border of Tokyo, Saitama, and Yamanashi Prefectures in Japan, known as one of the major peaks of the Okuchichibu Mountains and a popular hiking destination.
-
C.
Mount Ohiri
Mount Ohiri is the highest peak on the French Polynesian island of Taha'a in the Society Islands archipelago.
-
D.
Mount Maetokachi
Mount Maetokachi is a volcanic peak in Japan that forms part of the Tokachi Volcanic Group on the island of Hokkaido.
-
E.
Mount Okura
Mount Okura is a hill in Sapporo, Japan, best known for its large ski jumping stadium and panoramic views over the city.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d9d1c88190b01cd78b8be49384 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6351547e481909a875bba40651094 |
completed | April 20, 2026, 2:15 p.m. |
Created at: April 10, 2026, 1:40 p.m.