Triple
T14238342
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karamojong |
E352944
|
entity |
| Predicate | relatedGroup |
P37
|
FINISHED |
| Object | Turkana |
E81538
|
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: Turkana | Statement: [Karamojong, relatedGroup, Turkana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Turkana Context triple: [Karamojong, relatedGroup, Turkana]
-
A.
Magadi
Magadi is a historic town in Karnataka, India, known for its temples and as the former capital of the 16th-century ruler Kempegowda.
-
B.
Nansana
Nansana is a rapidly growing urban municipality in Uganda that forms part of the Greater Kampala metropolitan area.
-
C.
Lake Turkana
chosen
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.
-
D.
Ogaden
Ogaden is a historically contested, ethnically Somali-inhabited region in eastern Ethiopia known for its arid landscape and recurring conflicts over autonomy and control.
-
E.
Apswa
Apswa is the endonym used by the Abkhaz people to refer to themselves and their language.
- 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_69d8278adc7c8190a9218d69bce3c4e6 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de62422e28819089e7115052a28c96 |
completed | April 14, 2026, 3:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd281f80548190ad489c418f27e82c |
completed | May 8, 2026, 12:02 a.m. |
Created at: April 10, 2026, 1:08 a.m.