Triple

T28361260
Position Surface form Disambiguated ID Type / Status
Subject Kenya (former provinces system) E718367 entity
Predicate capitalOfWesternProvince P87043 FINISHED
Object Kakamega
Kakamega is a town in western Kenya known as a commercial and administrative center near the Kakamega Forest, the country’s only tropical rainforest.
E1815028 NE FINISHED

How this triple was built (3 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: Kakamega | Statement: [Kenya (former provinces system), capitalOfWesternProvince, Kakamega]
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: Kakamega
Triple: [Kenya (former provinces system), capitalOfWesternProvince, Kakamega]
Generated description
Kakamega is a town in western Kenya known as a commercial and administrative center near the Kakamega Forest, the country’s only tropical rainforest.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: capitalOfWesternProvince
Context triple: [Kenya (former provinces system), capitalOfWesternProvince, Kakamega]
  • A. capitalOfEasternProvince
    Indicates that one entity serves as the capital city or administrative center of a specified eastern province.
  • B. provinceCapitalOfProvince chosen
    Indicates that one entity is the capital city of a specified province.
  • C. capitalOfSeniorateProvince
    Indicates that a city serves as the capital of a specified seniorate province within a political or administrative system.
  • D. countryCapitalOfProvince
    Indicates that a country serves as the capital or primary administrative center of a specified province.
  • E. countryCapitalProvince
    Indicates that a given province serves as the capital administrative region of a specified country.
  • F. None of above.

Provenance (6 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_69eff6ed5af48190be4e0adf298223e0 completed April 27, 2026, 11:53 p.m.
NER Named-entity recognition batch_69f6fb19063c81909466b329655c8583 completed May 3, 2026, 7:36 a.m.
NED1 Entity disambiguation (via context triple) batch_6a1627cd57b08190a4ebe241e1028de0 completed May 26, 2026, 11:07 p.m.
NEDg Description generation batch_6a16296c415481909d07531b0f111069 completed May 26, 2026, 11:14 p.m.
NED2 Entity disambiguation (via description) batch_6a162ae322588190b466b7f0783cca82 completed May 26, 2026, 11:21 p.m.
PD Predicate disambiguation batch_69f6f969b4cc8190afb473a2d8b110bc completed May 3, 2026, 7:29 a.m.
Created at: April 28, 2026, 12:52 a.m.