Triple

T9793769
Position Surface form Disambiguated ID Type / Status
Subject Nyanza region E237667 entity
Predicate hasLanguage P15 FINISHED
Object Ekegusii
Ekegusii is a Bantu language spoken primarily by the Abagusii people of western Kenya.
E820926 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: Ekegusii | Statement: [Nyanza region, hasLanguage, Ekegusii]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ekegusii
Context triple: [Nyanza region, hasLanguage, Ekegusii]
  • A. Akita
    Akita is a city in Japan’s Tōhoku region, serving as the capital of Akita Prefecture and known for its port, rice production, and traditional festivals.
  • B. Akita
    Akita is a large, powerful Japanese dog breed known for its loyalty, dignity, and strong protective instincts.
  • C. Ebisu
    Ebisu is a fashionable Tokyo neighborhood known for its upscale dining, craft beer scene, and convenient access via Ebisu Station near Shibuya.
  • D. Havu
    Havu are a Bantu-speaking ethnic group primarily inhabiting the Lake Kivu region of eastern Democratic Republic of the Congo, known for their farming, fishing, and rich cultural traditions.
  • E. Kotek
    Kotek is the surname of Tina Kotek, an American politician who has served as Governor of Oregon and previously as Speaker of the Oregon House of Representatives.
  • 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: Ekegusii
Triple: [Nyanza region, hasLanguage, Ekegusii]
Generated description
Ekegusii is a Bantu language spoken primarily by the Abagusii people of western Kenya.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ekegusii
Target entity description: Ekegusii is a Bantu language spoken primarily by the Abagusii people of western Kenya.
  • A. Akita
    Akita is a city in Japan’s Tōhoku region, serving as the capital of Akita Prefecture and known for its port, rice production, and traditional festivals.
  • B. Akita
    Akita is a large, powerful Japanese dog breed known for its loyalty, dignity, and strong protective instincts.
  • C. Ebisu
    Ebisu is a fashionable Tokyo neighborhood known for its upscale dining, craft beer scene, and convenient access via Ebisu Station near Shibuya.
  • D. Havu
    Havu are a Bantu-speaking ethnic group primarily inhabiting the Lake Kivu region of eastern Democratic Republic of the Congo, known for their farming, fishing, and rich cultural traditions.
  • E. Kotek
    Kotek is the surname of Tina Kotek, an American politician who has served as Governor of Oregon and previously as Speaker of the Oregon House of Representatives.
  • 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_69ca84dc04488190b9c91193976c0960 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda347b6bc8190a99b7dec1650cd46 completed April 1, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1c4368da88190a70e93ec4d6bef93 completed April 5, 2026, 2:08 a.m.
NEDg Description generation batch_69d1c4a087208190b81ae9d40de08ab9 completed April 5, 2026, 2:10 a.m.
NED2 Entity disambiguation (via description) batch_69d1c4fe71308190ac08e30c98611ed6 completed April 5, 2026, 2:12 a.m.
Created at: March 30, 2026, 8:28 p.m.