Triple

T1827990
Position Surface form Disambiguated ID Type / Status
Subject Kampala E40695 entity
Predicate hasHill P24292 FINISHED
Object Kibuli Hill
Kibuli Hill is one of the prominent hills in Kampala, Uganda, known for its historic mosque and significant Muslim community institutions.
E212932 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: Kibuli Hill | Statement: [Kampala, hasHill, Kibuli Hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kibuli Hill
Context triple: [Kampala, hasHill, Kibuli Hill]
  • A. Rubaga Hill
    Rubaga Hill is one of Kampala’s prominent historic hills, known as the seat of the Rubaga Cathedral and a major center of the Catholic Church in Uganda.
  • B. Kololo Hill
    Kololo Hill is an upscale residential and diplomatic neighborhood in Kampala, Uganda, known for its embassies, luxury homes, and city views.
  • C. Namirembe Hill
    Namirembe Hill is a prominent hill in Kampala, Uganda, best known as the historic site of St. Paul's Cathedral, the seat of the Anglican Church in the country.
  • D. Nakasero Hill
    Nakasero Hill is an upscale, central neighborhood in Kampala known for hosting government offices, embassies, luxury hotels, and commercial centers.
  • E. Mawenzi
    Mawenzi is the jagged, eroded eastern peak of Mount Kilimanjaro and one of its three main volcanic cones.
  • 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: Kibuli Hill
Triple: [Kampala, hasHill, Kibuli Hill]
Generated description
Kibuli Hill is one of the prominent hills in Kampala, Uganda, known for its historic mosque and significant Muslim community institutions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kibuli Hill
Target entity description: Kibuli Hill is one of the prominent hills in Kampala, Uganda, known for its historic mosque and significant Muslim community institutions.
  • A. Rubaga Hill
    Rubaga Hill is one of Kampala’s prominent historic hills, known as the seat of the Rubaga Cathedral and a major center of the Catholic Church in Uganda.
  • B. Kololo Hill
    Kololo Hill is an upscale residential and diplomatic neighborhood in Kampala, Uganda, known for its embassies, luxury homes, and city views.
  • C. Namirembe Hill
    Namirembe Hill is a prominent hill in Kampala, Uganda, best known as the historic site of St. Paul's Cathedral, the seat of the Anglican Church in the country.
  • D. Nakasero Hill
    Nakasero Hill is an upscale, central neighborhood in Kampala known for hosting government offices, embassies, luxury hotels, and commercial centers.
  • E. Mawenzi
    Mawenzi is the jagged, eroded eastern peak of Mount Kilimanjaro and one of its three main volcanic cones.
  • 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_69adead6888081909f89704f0c070d68 completed March 8, 2026, 9:32 p.m.
NEDg Description generation batch_69adebc28ae88190bd954d9634f08059 completed March 8, 2026, 9:36 p.m.
NED2 Entity disambiguation (via description) batch_69adec25a87081908f098df81de6eafb completed March 8, 2026, 9:37 p.m.
Created at: March 4, 2026, 7:32 p.m.