Triple

T21053699
Position Surface form Disambiguated ID Type / Status
Subject Ngulu language E518652 entity
Predicate hasAlternateName P39 FINISHED
Object Kinguulu
Kinguulu is an alternate name for the Ngulu language, a Bantu language spoken in parts of Tanzania.
E1465786 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: Kinguulu | Statement: [Ngulu language, hasAlternateName, Kinguulu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kinguulu
Context triple: [Ngulu language, hasAlternateName, Kinguulu]
  • A. Kangulumira
    Kangulumira is a small town in central Uganda located within Kayunga District.
  • B. Kingunda
    Kingunda is a variant form of the female given name Kunegunda, used in certain linguistic or regional contexts.
  • C. Kusaasi
    The Kusaasi are an ethnic group of northern Ghana and southern Burkina Faso, known for their distinct cultural traditions and as native speakers of the Kusaal language.
  • D. Kasangati
    Kasangati is a town in central Uganda that serves as a growing commercial and residential hub within the Greater Kampala metropolitan area.
  • E. Enbilulu
    Enbilulu is a Mesopotamian deity associated with irrigation, canals, and the management of rivers and agricultural waters.
  • 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: Kinguulu
Triple: [Ngulu language, hasAlternateName, Kinguulu]
Generated description
Kinguulu is an alternate name for the Ngulu language, a Bantu language spoken in parts of Tanzania.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kinguulu
Target entity description: Kinguulu is an alternate name for the Ngulu language, a Bantu language spoken in parts of Tanzania.
  • A. Kangulumira
    Kangulumira is a small town in central Uganda located within Kayunga District.
  • B. Kingunda
    Kingunda is a variant form of the female given name Kunegunda, used in certain linguistic or regional contexts.
  • C. Kusaasi
    The Kusaasi are an ethnic group of northern Ghana and southern Burkina Faso, known for their distinct cultural traditions and as native speakers of the Kusaal language.
  • D. Kasangati
    Kasangati is a town in central Uganda that serves as a growing commercial and residential hub within the Greater Kampala metropolitan area.
  • E. Enbilulu
    Enbilulu is a Mesopotamian deity associated with irrigation, canals, and the management of rivers and agricultural waters.
  • 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_69e0b5053ac48190921529544959e906 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fd7e087c81908712ddc63e8b1e6c completed April 21, 2026, 4:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a095a4bf5048190867f67140395a045 completed May 17, 2026, 6:03 a.m.
NEDg Description generation batch_6a095b1cb97c8190b3ba95373bd21056 completed May 17, 2026, 6:07 a.m.
NED2 Entity disambiguation (via description) batch_6a095bf3efa4819089368a3e80a41e15 completed May 17, 2026, 6:11 a.m.
Created at: April 16, 2026, 2:36 p.m.