Triple
T19672478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanzam Highway |
E472366
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Mbeya |
—
|
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: Mbeya | Statement: [Tanzam Highway, connectsTo, Mbeya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mbeya Context triple: [Tanzam Highway, connectsTo, Mbeya]
-
A.
Mbeya
chosen
Mbeya is a major city in southwestern Tanzania, serving as a commercial and transport hub near the Zambian border.
-
B.
Mikocheni
Mikocheni is a residential and commercial neighborhood in Dar es Salaam, Tanzania, known for its middle-class housing, offices, and educational institutions.
-
C.
Masindi
Masindi is a town in western Uganda that serves as a key gateway and service center for visitors to Murchison Falls National Park.
-
D.
Mbabane
Mbabane is the largest city and administrative center of Eswatini, located in the country's western highlands.
-
E.
Msikaba
Msikaba is a coastal area in South Africa’s Eastern Cape known for its rugged shoreline, river gorge, and rich biodiversity near the Mkambati Nature Reserve.
- 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_69d8e514f2e08190ba70a4449519d218 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6416d61008190af531c6d346d7da1 |
completed | April 20, 2026, 3:08 p.m. |
Created at: April 10, 2026, 1:45 p.m.