Triple
T25447530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nairobi–Karachi |
E637676
|
entity |
| Predicate | linkedCityCountry2 |
P39274
|
FINISHED |
| Object | Karachi, Pakistan |
—
|
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: Karachi, Pakistan | Statement: [Nairobi–Karachi, linkedCityCountry2, Karachi, Pakistan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedCityCountry2 Context triple: [Nairobi–Karachi, linkedCityCountry2, Karachi, Pakistan]
-
A.
linkedCity
Indicates that two entities are associated with each other through a specific city, such as being located in, connected via, or related by that city.
-
B.
countryOfCityReferredTo
chosen
Indicates that one entity is the country in which the referenced city entity is located.
-
C.
connectsCapitalOf
Indicates a relationship where one entity serves as the capital city of another entity, linking the capital to the political or administrative unit it represents.
-
D.
hasCountryCapitalConnection
Indicates a relationship in which a specific country is associated with its official capital city.
-
E.
linkedCityInEurope
Indicates that there is an association or connection between entities that specifically involves a city located in Europe.
- 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_69e75db7c5048190b8da9cd7eeedb610 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f676c440708190a4b9974e95d2291a |
completed | May 2, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69f675fd59608190b246383435e68fce |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 21, 2026, 2:02 p.m.