Triple
T9222174
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ol Doinyo Lengai |
E221588
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Lake Natron |
E203034
|
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: Lake Natron | Statement: [Ol Doinyo Lengai, locatedNear, Lake Natron]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lake Natron Context triple: [Ol Doinyo Lengai, locatedNear, Lake Natron]
-
A.
Lake Natron
chosen
Lake Natron is a highly alkaline, shallow salt lake in northern Tanzania, renowned for its striking red coloration and as a critical breeding ground for lesser flamingos.
-
B.
Lake Bogoria
Lake Bogoria is a saline, alkaline lake in Kenya’s Rift Valley famous for its hot springs, geysers, and large flocks of flamingos.
-
C.
Lake Manyara
Lake Manyara is a shallow alkaline lake in northern Tanzania, renowned for its diverse birdlife, large flocks of flamingos, and the surrounding Lake Manyara National Park.
-
D.
Lake Nakuru
Lake Nakuru is a shallow alkaline lake in Kenya’s Rift Valley, famed for its large populations of flamingos and diverse wildlife within Lake Nakuru National Park.
-
E.
Lake Turkana
Lake Turkana is a large, saline lake in Kenya’s arid north, renowned for its striking turquoise waters, rich biodiversity, and significant archaeological sites along its shores.
- 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_69ca83ec8db08190a9110df8232885d2 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccda76e3648190af9e24381db7679a |
completed | April 1, 2026, 8:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d066384a908190b833d4ae5b3c5074 |
completed | April 4, 2026, 1:15 a.m. |
Created at: March 30, 2026, 7:28 p.m.