Triple
T7723946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | mainland Tanzania |
E175082
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Dodoma |
E107054
|
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: Dodoma | Statement: [mainland Tanzania, capital, Dodoma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dodoma Context triple: [mainland Tanzania, capital, Dodoma]
-
A.
Dodoma
chosen
Dodoma is the political and administrative capital city of Tanzania, located in the country’s central region.
-
B.
Dar es Salaam
Dar es Salaam is a major coastal metropolis on the Indian Ocean and the principal economic and commercial hub of Tanzania.
-
C.
Arusha, Tanzania
Arusha, Tanzania is a major city in northern Tanzania known as a diplomatic hub and gateway to popular safari destinations and Mount Kilimanjaro.
-
D.
Dodoma Region
Dodoma Region is an administrative region in central Tanzania that includes the national capital city, Dodoma.
-
E.
Nairobi
Nairobi is the capital and largest city of Kenya, serving as a major political, economic, and cultural hub in East Africa.
- 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_69c6995d541c81909eaa646b1a8369a9 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c702f39fa48190b7b8a09446b5cf78 |
completed | March 27, 2026, 10:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8b51faa348190b4fa0b5a307c83db |
completed | March 29, 2026, 5:14 a.m. |
Created at: March 27, 2026, 4:05 p.m.