Triple

T2160279
Position Surface form Disambiguated ID Type / Status
Subject Nzebi E47983 entity
Predicate hasNeighborLanguage P16383 FINISHED
Object Mbede
Mbede is a Bantu language spoken in Central Africa, primarily in Gabon and neighboring regions.
 E240268 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: Mbede | Statement: [Nzebi, hasNeighborLanguage, Mbede]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mbede
Context triple: [Nzebi, hasNeighborLanguage, Mbede]
  • A. Negombo
    Negombo is a coastal city in western Sri Lanka known historically as a strategic colonial port and today for its fishing industry and beach tourism.
  • B. Kumba
    Kumba is a renowned steel roller coaster at Busch Gardens Tampa Bay, famous for its intense inversions and smooth, high-speed layout.
  • C. Mekè
    Mekè is a regional dialect of the Fang language spoken by Fang communities in Central Africa.
  • D. Bagana
    Bagana is an active stratovolcano on Bougainville Island in Papua New Guinea, known for its frequent eruptions and extensive lava flows.
  • E. Bisha
    Bisha is a major inland city in southwestern Saudi Arabia known for its agricultural production and strategic location within the Asir region.
  • 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: Mbede
Triple: [Nzebi, hasNeighborLanguage, Mbede]
Generated description
Mbede is a Bantu language spoken in Central Africa, primarily in Gabon and neighboring regions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mbede
Target entity description: Mbede is a Bantu language spoken in Central Africa, primarily in Gabon and neighboring regions.
  • A. Negombo
    Negombo is a coastal city in western Sri Lanka known historically as a strategic colonial port and today for its fishing industry and beach tourism.
  • B. Kumba
    Kumba is a renowned steel roller coaster at Busch Gardens Tampa Bay, famous for its intense inversions and smooth, high-speed layout.
  • C. Mekè
    Mekè is a regional dialect of the Fang language spoken by Fang communities in Central Africa.
  • D. Bagana
    Bagana is an active stratovolcano on Bougainville Island in Papua New Guinea, known for its frequent eruptions and extensive lava flows.
  • E. Bisha
    Bisha is a major inland city in southwestern Saudi Arabia known for its agricultural production and strategic location within the Asir region.
  • 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_69a88a1d1fd8819088b34990d69a712f completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abbe8894d481908eda9363fd36fea6 completed March 7, 2026, 5:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae58e9ceb08190871ff9c57ece23c0 completed March 9, 2026, 5:21 a.m.
NEDg Description generation batch_69ae5a3db428819083d73b4295c4e829 completed March 9, 2026, 5:27 a.m.
NED2 Entity disambiguation (via description) batch_69ae5a9b72188190bceb31975461206f completed March 9, 2026, 5:28 a.m.
Created at: March 4, 2026, 7:45 p.m.