Triple

T20954335
Position Surface form Disambiguated ID Type / Status
Subject Kamiriithu E516060 entity
Predicate near P350 FINISHED
Object Limuru town NE NERFINISHED

How this triple was built (2 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: Limuru town | Statement: [Kamiriithu, near, Limuru town]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Limuru town
Context triple: [Kamiriithu, near, Limuru town]
  • A. Limuru chosen
    Limuru is a highland town in central Kenya known for its cool climate, tea plantations, and proximity to Nairobi.
  • B. Yaunde
    Yaunde is an alternative name for Kolo, likely referring to the same place or entity under a different local or historical designation.
  • C. Tsavo town
    Tsavo town is a small settlement in southeastern Kenya that serves as a gateway to the nearby Tsavo East and Tsavo West National Parks.
  • D. Mogoro
    Mogoro is a small town and municipality in central-western Sardinia, Italy, known for its traditional crafts and wine production.
  • E. Ambaji town
    Ambaji town is a prominent Hindu pilgrimage center in Gujarat, India, best known for its revered Ambaji Temple dedicated to the goddess Amba.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4fcd678819087a304291f14330a completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fae154a481909f235165a46d0910 completed April 21, 2026, 4:19 a.m.
Created at: April 16, 2026, 1:28 p.m.