Triple
T13151030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kibo summit crater |
E312465
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Uhuru Peak |
E379828
|
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: Uhuru Peak | Statement: [Kibo summit crater, contains, Uhuru Peak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Uhuru Peak Context triple: [Kibo summit crater, contains, Uhuru Peak]
-
A.
Uhuru Peak
chosen
Uhuru Peak is the highest summit of Mount Kilimanjaro and the tallest point in Africa, renowned as a major goal for trekkers and climbers worldwide.
-
B.
Karatu
Karatu is a small town in northern Tanzania that serves as a popular gateway to the Ngorongoro Conservation Area and Serengeti National Park.
-
C.
Mount Ntringui
Mount Ntringui is a volcanic peak on the island of Anjouan in the Comoros, known for its lush forests and prominence in the island’s rugged landscape.
-
D.
Mount Saramati
Mount Saramati is a prominent peak in Northeast India, known for its rugged terrain, rich biodiversity, and panoramic views over the India–Myanmar border region.
-
E.
Mount Kisokoma
Mount Kisokoma is a prominent alpine peak in Japan’s Central Alps, known for its scenic highland landscapes and popular hiking routes.
- 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_69d806aabde48190899e13e41659cae5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98bd1fc408190b4b5ca973bcee403 |
completed | April 10, 2026, 11:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f75d7edb40819095dfa45d3c61a0e3 |
completed | May 3, 2026, 2:36 p.m. |
Created at: April 9, 2026, 9:11 p.m.