Triple
T1827986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kampala |
E40695
|
entity |
| Predicate | hasHill |
P24292
|
FINISHED |
| Object |
Kololo Hill
Kololo Hill is an upscale residential and diplomatic neighborhood in Kampala, Uganda, known for its embassies, luxury homes, and city views.
|
E206537
|
NE FINISHED |
How this triple was built (4 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: Kololo Hill | Statement: [Kampala, hasHill, Kololo Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kololo Hill Context triple: [Kampala, hasHill, Kololo Hill]
-
A.
Nakasero Hill
Nakasero Hill is an upscale, central neighborhood in Kampala known for hosting government offices, embassies, luxury hotels, and commercial centers.
-
B.
Birsay Hills
Birsay Hills are a range of low, rolling hills forming the highest ground on Orkney’s Mainland in Scotland, known for their open moorland and coastal views.
-
C.
Murahwa Hill
Murahwa Hill is a prominent historical and archaeological site near Mutare, Zimbabwe, known for its ancient rock shelters, rock art, and cultural significance to local communities.
-
D.
Piekberg
Piekberg is a low, wooded hill on the German island of Rügen, notable as its highest natural elevation.
-
E.
Erg Chigaga
Erg Chigaga is a vast, remote dune field in southern Morocco known for its towering sand dunes and desert wilderness landscapes.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kololo Hill Triple: [Kampala, hasHill, Kololo Hill]
Generated description
Kololo Hill is an upscale residential and diplomatic neighborhood in Kampala, Uganda, known for its embassies, luxury homes, and city views.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kololo Hill Target entity description: Kololo Hill is an upscale residential and diplomatic neighborhood in Kampala, Uganda, known for its embassies, luxury homes, and city views.
-
A.
Nakasero Hill
Nakasero Hill is an upscale, central neighborhood in Kampala known for hosting government offices, embassies, luxury hotels, and commercial centers.
-
B.
Birsay Hills
Birsay Hills are a range of low, rolling hills forming the highest ground on Orkney’s Mainland in Scotland, known for their open moorland and coastal views.
-
C.
Murahwa Hill
Murahwa Hill is a prominent historical and archaeological site near Mutare, Zimbabwe, known for its ancient rock shelters, rock art, and cultural significance to local communities.
-
D.
Piekberg
Piekberg is a low, wooded hill on the German island of Rügen, notable as its highest natural elevation.
-
E.
Erg Chigaga
Erg Chigaga is a vast, remote dune field in southern Morocco known for its towering sand dunes and desert wilderness landscapes.
- F. None of above. chosen
Provenance (5 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_69a8864644bc8190b2358ab897194ac1 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb01191208190a7eaf3036638ec40 |
completed | March 7, 2026, 4:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adc9b24f448190a3aa5a85a9106d71 |
completed | March 8, 2026, 7:10 p.m. |
| NEDg | Description generation | batch_69adcc55db8481909b5680230a61a4c1 |
completed | March 8, 2026, 7:21 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69adccf2b56c8190bf2de8f8bcbb4837 |
completed | March 8, 2026, 7:24 p.m. |
Created at: March 4, 2026, 7:32 p.m.