Triple

T1187772
Position Surface form Disambiguated ID Type / Status
Subject Bantu languages E25285 entity
Predicate ancestorLanguage P6149 FINISHED
Object Proto-Bantu
Proto-Bantu is the reconstructed common ancestor of the Bantu language family, hypothesized through comparative linguistic methods to represent their original phonology, grammar, and core vocabulary.
E152878 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: Proto-Bantu | Statement: [Bantu languages, ancestorLanguage, Proto-Bantu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Proto-Bantu
Context triple: [Bantu languages, ancestorLanguage, Proto-Bantu]
  • A. Bantu languages
    Bantu languages are a large family of closely related languages spoken across much of central, eastern, and southern Africa, known for features like noun class systems and widespread mutual influences among neighboring tongues.
  • B. Nguni languages
    The Nguni languages are a group of closely related Bantu languages of southern Africa that include major tongues such as Zulu, Xhosa, Swati, and Ndebele.
  • C. Niger–Congo languages
    The Niger–Congo languages form one of the world’s largest language families, encompassing hundreds of related languages spoken across much of sub-Saharan Africa, including major groups like Bantu.
  • D. Benue–Congo languages
    The Benue–Congo languages are a large and diverse branch of African languages that include the widespread Bantu family and are spoken across much of sub-Saharan Africa.
  • E. Grassfields languages
    Grassfields languages are a group of closely related Southern Bantoid languages spoken primarily in the Grassfields region of western Cameroon.
  • 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: Proto-Bantu
Triple: [Bantu languages, ancestorLanguage, Proto-Bantu]
Generated description
Proto-Bantu is the reconstructed common ancestor of the Bantu language family, hypothesized through comparative linguistic methods to represent their original phonology, grammar, and core vocabulary.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Proto-Bantu
Target entity description: Proto-Bantu is the reconstructed common ancestor of the Bantu language family, hypothesized through comparative linguistic methods to represent their original phonology, grammar, and core vocabulary.
  • A. Bantu languages
    Bantu languages are a large family of closely related languages spoken across much of central, eastern, and southern Africa, known for features like noun class systems and widespread mutual influences among neighboring tongues.
  • B. Nguni languages
    The Nguni languages are a group of closely related Bantu languages of southern Africa that include major tongues such as Zulu, Xhosa, Swati, and Ndebele.
  • C. Niger–Congo languages
    The Niger–Congo languages form one of the world’s largest language families, encompassing hundreds of related languages spoken across much of sub-Saharan Africa, including major groups like Bantu.
  • D. Benue–Congo languages
    The Benue–Congo languages are a large and diverse branch of African languages that include the widespread Bantu family and are spoken across much of sub-Saharan Africa.
  • E. Grassfields languages
    Grassfields languages are a group of closely related Southern Bantoid languages spoken primarily in the Grassfields region of western Cameroon.
  • 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_69a49427d98881908646d6c63b8cea1e completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bd568cf481908d10cf19a3ce28f3 completed March 1, 2026, 10:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69acbf15b1e08190a9c75bc7bc467197 completed March 8, 2026, 12:13 a.m.
NEDg Description generation batch_69acbfa308148190a27f5433abcb2a18 completed March 8, 2026, 12:15 a.m.
NED2 Entity disambiguation (via description) batch_69acc0912bf481909bd27111b4daaa0b completed March 8, 2026, 12:19 a.m.
Created at: March 1, 2026, 7:45 p.m.