Triple

T14170084
Position Surface form Disambiguated ID Type / Status
Subject Meru people E351181 entity
Predicate subgroup P10 FINISHED
Object Tharaka
Tharaka are a distinct subgroup of the Meru people of Kenya, known for their unique language variety and cultural traditions.
E1086411 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: Tharaka | Statement: [Meru people, subgroup, Tharaka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tharaka
Context triple: [Meru people, subgroup, Tharaka]
  • A. Nagaina
    Nagaina is the deadly female cobra antagonist in Rudyard Kipling’s “Rikki-Tikki-Tavi,” known for plotting against the human family and their mongoose protector.
  • B. Nungua
    Nungua is a coastal town and suburb of Accra in southern Ghana, known for its fishing community and vibrant local culture.
  • C. Ruaraka
    Ruaraka is a mixed residential, industrial, and commercial suburb in northeastern Nairobi, Kenya, known for its breweries, factories, and proximity to major transport routes.
  • D. Tamba
    Tamba is a city located in Hyogo Prefecture, Japan, known for its rural landscapes, traditional pottery, and historical sites.
  • E. Kayeli
    Kayeli is an extinct Austronesian language that was once spoken on Buru Island in Indonesia.
  • 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: Tharaka
Triple: [Meru people, subgroup, Tharaka]
Generated description
Tharaka are a distinct subgroup of the Meru people of Kenya, known for their unique language variety and cultural traditions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tharaka
Target entity description: Tharaka are a distinct subgroup of the Meru people of Kenya, known for their unique language variety and cultural traditions.
  • A. Nagaina
    Nagaina is the deadly female cobra antagonist in Rudyard Kipling’s “Rikki-Tikki-Tavi,” known for plotting against the human family and their mongoose protector.
  • B. Nungua
    Nungua is a coastal town and suburb of Accra in southern Ghana, known for its fishing community and vibrant local culture.
  • C. Ruaraka
    Ruaraka is a mixed residential, industrial, and commercial suburb in northeastern Nairobi, Kenya, known for its breweries, factories, and proximity to major transport routes.
  • D. Tamba
    Tamba is a city located in Hyogo Prefecture, Japan, known for its rural landscapes, traditional pottery, and historical sites.
  • E. Kayeli
    Kayeli is an extinct Austronesian language that was once spoken on Buru Island in Indonesia.
  • 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_69d8278834a08190b0f1784e58d7b99c completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61b472288190b4a271daa54aa6cd completed April 14, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd193dbbcc819082043d92c174164c completed May 7, 2026, 10:59 p.m.
NEDg Description generation batch_69fd1d57dfa88190a4cd9b6fceddbc3b completed May 7, 2026, 11:16 p.m.
NED2 Entity disambiguation (via description) batch_69fd1e267dcc819087a24cbfea2736db completed May 7, 2026, 11:20 p.m.
Created at: April 10, 2026, 1:01 a.m.