Triple

T15786184
Position Surface form Disambiguated ID Type / Status
Subject Northern Kenya E382744 entity
Predicate hasMajorTown P316 FINISHED
Object Marsabit
Marsabit is a remote market and administrative town in northern Kenya, known as a gateway to Marsabit National Park and its surrounding arid highlands.
 E1196185 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: Marsabit | Statement: [Northern Kenya, hasMajorTown, Marsabit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marsabit
Context triple: [Northern Kenya, hasMajorTown, Marsabit]
  • A. Isiolo
    Isiolo is a town in central Kenya that serves as a key transport and commercial hub linking the country’s northern regions with the rest of the nation.
  • B. Kajiado
    Kajiado is a town in southern Kenya that serves as an administrative and commercial center for the surrounding Maasai-inhabited region.
  • C. Wazaramo
    Wazaramo are a Bantu-speaking ethnic group native to the coastal and near-coastal regions around Dar es Salaam in eastern Tanzania.
  • D. Nakuru
    Nakuru is a prominent Kenyan city in the Rift Valley region, known for its proximity to Lake Nakuru National Park and its role as an important agricultural and commercial center.
  • E. Taveta
    Taveta is a key border town in southern Kenya near Tanzania, serving as an important regional trade and transport hub.
  • 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: Marsabit
Triple: [Northern Kenya, hasMajorTown, Marsabit]
Generated description
Marsabit is a remote market and administrative town in northern Kenya, known as a gateway to Marsabit National Park and its surrounding arid highlands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marsabit
Target entity description: Marsabit is a remote market and administrative town in northern Kenya, known as a gateway to Marsabit National Park and its surrounding arid highlands.
  • A. Isiolo
    Isiolo is a town in central Kenya that serves as a key transport and commercial hub linking the country’s northern regions with the rest of the nation.
  • B. Kajiado
    Kajiado is a town in southern Kenya that serves as an administrative and commercial center for the surrounding Maasai-inhabited region.
  • C. Wazaramo
    Wazaramo are a Bantu-speaking ethnic group native to the coastal and near-coastal regions around Dar es Salaam in eastern Tanzania.
  • D. Nakuru
    Nakuru is a prominent Kenyan city in the Rift Valley region, known for its proximity to Lake Nakuru National Park and its role as an important agricultural and commercial center.
  • E. Taveta
    Taveta is a key border town in southern Kenya near Tanzania, serving as an important regional trade and transport hub.
  • 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_69d86da16e188190b89af699f1ed0bfe completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0540380448190a025338f0e62e6d1 completed April 16, 2026, 3:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff28f63c88190968ecbd4706b1331 completed May 10, 2026, 2:50 a.m.
NEDg Description generation batch_69fff35ded288190b4d261358f1661cb completed May 10, 2026, 2:54 a.m.
NED2 Entity disambiguation (via description) batch_69fff3f2760c8190a58fedc2798614ae completed May 10, 2026, 2:56 a.m.
Created at: April 10, 2026, 4:48 a.m.