Triple

T2391168
Position Surface form Disambiguated ID Type / Status
Subject Punu E48945 entity
Predicate closelyRelatedTo P37 FINISHED
Object Sangu (Bantu language)
Sangu is a Bantu language of Central Africa, known for its noun class system and close linguistic ties to neighboring Bantu languages such as Punu.
 E264181 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: Sangu (Bantu language) | Statement: [Punu, closelyRelatedTo, Sangu (Bantu language)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sangu (Bantu language)
Context triple: [Punu, closelyRelatedTo, Sangu (Bantu language)]
  • A. Bantu T languages
    Bantu T languages are a subgroup of Bantu languages spoken primarily in parts of southern and eastern Africa, characterized by shared phonological and grammatical features within the wider Niger-Congo language family.
  • B. Southern Bantu languages
    Southern Bantu languages are a major branch of the Bantu language family spoken primarily in southern Africa, including well-known languages such as Zulu, Xhosa, and Shona.
  • C. Bantu K languages
    Bantu K languages are a subgroup of the Bantu language family spoken primarily in parts of Central and Southern Africa, known for their shared grammatical structures and noun class systems.
  • D. Sukuma language
    The Sukuma language is a Bantu language spoken primarily by the Sukuma people in northwestern Tanzania.
  • E. Bantu W languages
    Bantu W languages are a subgroup of Bantu languages spoken primarily in parts of Central and Southern Africa, characterized by shared phonological and grammatical features within the wider Niger-Congo language family.
  • 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: Sangu (Bantu language)
Triple: [Punu, closelyRelatedTo, Sangu (Bantu language)]
Generated description
Sangu is a Bantu language of Central Africa, known for its noun class system and close linguistic ties to neighboring Bantu languages such as Punu.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sangu (Bantu language)
Target entity description: Sangu is a Bantu language of Central Africa, known for its noun class system and close linguistic ties to neighboring Bantu languages such as Punu.
  • A. Bantu T languages
    Bantu T languages are a subgroup of Bantu languages spoken primarily in parts of southern and eastern Africa, characterized by shared phonological and grammatical features within the wider Niger-Congo language family.
  • B. Southern Bantu languages
    Southern Bantu languages are a major branch of the Bantu language family spoken primarily in southern Africa, including well-known languages such as Zulu, Xhosa, and Shona.
  • C. Bongo language
    The Bongo language is a Central Sudanic language spoken by the Bongo people of South Sudan.
  • D. Bantu K languages
    Bantu K languages are a subgroup of the Bantu language family spoken primarily in parts of Central and Southern Africa, known for their shared grammatical structures and noun class systems.
  • E. Sukuma language
    The Sukuma language is a Bantu language spoken primarily by the Sukuma people in northwestern Tanzania.
  • 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_69a88aa5f63081908d07fd302029fcbd completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc87457388190822d5506327db8f2 completed March 7, 2026, 6:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69aeb3d4f0608190bcc77a67fa85b963 completed March 9, 2026, 11:49 a.m.
NEDg Description generation batch_69aeb79b249c8190818bc4daf9eebd2a completed March 9, 2026, 12:05 p.m.
NED2 Entity disambiguation (via description) batch_69aeb843b8e88190b5e4417a64ce8f49 completed March 9, 2026, 12:08 p.m.
Created at: March 4, 2026, 7:57 p.m.