Triple
T25699511
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nairobi–Dar es Salaam |
E644417
|
entity |
| Predicate | connectsLargestCityOf |
P94566
|
FINISHED |
| Object | Tanzania |
—
|
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: Tanzania | Statement: [Nairobi–Dar es Salaam, connectsLargestCityOf, Tanzania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsLargestCityOf Context triple: [Nairobi–Dar es Salaam, connectsLargestCityOf, Tanzania]
-
A.
connectsLargestCitiesOf
chosen
Indicates a relationship where something (typically a route, network, or infrastructure) links together the largest cities within a specified region or set.
-
B.
connectsMajorCity
Indicates that one entity serves as a link or route providing direct connection to a major city.
-
C.
areLargestCitiesOf
Indicates that the subject entities are the largest cities within the regions or countries specified by the object entities.
-
D.
largestCity
Indicates that one city is the most populous or significant urban center within a specified region or entity.
-
E.
connectsMajorCityState
Indicates that something serves as a link or route between a major city and the state it belongs to.
- F. None of above.
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_69e77e82c9bc8190893090b2f6c64f1d |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 21, 2026, 8:42 p.m.