Triple

T8309672
Position Surface form Disambiguated ID Type / Status
Subject Kagera Region E194558 entity
Predicate hasEthnicGroup P1898 FINISHED
Object Hangaza
The Hangaza are an ethnic group native to northwestern Tanzania, primarily inhabiting the Kagera Region near the border with Rwanda and Uganda.
 E725056 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: Hangaza | Statement: [Kagera Region, hasEthnicGroup, Hangaza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hangaza
Context triple: [Kagera Region, hasEthnicGroup, Hangaza]
  • A. Manzala
    Manzala is a town in northeastern Egypt situated near Lake Manzala and known for its fishing and agricultural activities.
  • B. Busayrah
    Busayrah is a town in eastern Syria situated along the Khabur River, historically important as a local agricultural and trading center.
  • C. Zigra
    Zigra is a monstrous alien shark-like kaiju from the Gamera film series, known for invading Earth and battling the giant turtle guardian.
  • D. Hakitia
    Hakitia is a Judeo-Spanish dialect historically spoken by North African Sephardic Jews, blending Old Spanish with Hebrew and elements of Arabic.
  • E. Montaza
    Montaza is a coastal district and popular recreational area in Alexandria, Egypt, known for its historic royal palace, expansive gardens, and Mediterranean beaches.
  • 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: Hangaza
Triple: [Kagera Region, hasEthnicGroup, Hangaza]
Generated description
The Hangaza are an ethnic group native to northwestern Tanzania, primarily inhabiting the Kagera Region near the border with Rwanda and Uganda.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hangaza
Target entity description: The Hangaza are an ethnic group native to northwestern Tanzania, primarily inhabiting the Kagera Region near the border with Rwanda and Uganda.
  • A. Manzala
    Manzala is a town in northeastern Egypt situated near Lake Manzala and known for its fishing and agricultural activities.
  • B. Busayrah
    Busayrah is a town in eastern Syria situated along the Khabur River, historically important as a local agricultural and trading center.
  • C. Zigra
    Zigra is a monstrous alien shark-like kaiju from the Gamera film series, known for invading Earth and battling the giant turtle guardian.
  • D. Hakitia
    Hakitia is a Judeo-Spanish dialect historically spoken by North African Sephardic Jews, blending Old Spanish with Hebrew and elements of Arabic.
  • E. Montaza
    Montaza is a coastal district and popular recreational area in Alexandria, Egypt, known for its historic royal palace, expansive gardens, and Mediterranean beaches.
  • 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_69ca82e613e88190bf8139669bbd0d53 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7f2d2c30819095075940479b75a7 completed March 31, 2026, 8 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd95665390819089c8becad018cf51 completed April 1, 2026, 10 p.m.
NEDg Description generation batch_69cda62070888190b55b3f54d29e28e7 completed April 1, 2026, 11:11 p.m.
NED2 Entity disambiguation (via description) batch_69cdb21a65d88190a19dd41f95d173c8 completed April 2, 2026, 12:02 a.m.
Created at: March 30, 2026, 5:54 p.m.