Triple

T14713707
Position Surface form Disambiguated ID Type / Status
Subject Ondo Kingdom E345620 entity
Predicate capital P234 FINISHED
Object Ondo 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: Ondo | Statement: [Ondo Kingdom, capital, Ondo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ondo
Context triple: [Ondo Kingdom, capital, Ondo]
  • A. Ondo chosen
    Ondo is a historic Yoruba town in southwestern Nigeria known for its traditional monarchy, cultural heritage, and role as a regional commercial center.
  • B. Ondo State
    Ondo State is a coastal state in southwestern Nigeria known for its oil-producing areas, diverse ethnic communities, and significant role within the Niger Delta region.
  • C. Ogun State
    Ogun State is a southwestern Nigerian state known as a key Yoruba cultural heartland and an important industrial and educational hub.
  • D. Osun State
    Osun State is a southwestern Nigerian state that is a cultural and historical heartland of the Yoruba people, known for its traditional festivals and religious heritage.
  • E. Oye-Ekiti
    Oye-Ekiti is a town in Ekiti State, southwestern Nigeria, known as an educational hub and administrative center in the region.
  • 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_69d822e4a8c08190a155df736bb7bc13 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb98513b081908b230f6ac79c72ad completed April 14, 2026, 10:02 p.m.
Created at: April 10, 2026, 1:29 a.m.