Triple

T16767734
Position Surface form Disambiguated ID Type / Status
Subject Akassa language E407509 entity
Predicate hasAlternativeName P39 FINISHED
Object Akassa (Ijo)
Akassa (Ijo) is an endangered Ijoid language spoken by the Akassa people in the Niger Delta region of southern Nigeria.
E1231992 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: Akassa (Ijo) | Statement: [Akassa language, hasAlternativeName, Akassa (Ijo)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akassa (Ijo)
Context triple: [Akassa language, hasAlternativeName, Akassa (Ijo)]
  • A. Kamen-na-Obi
    Kamen-na-Obi is a town in Altai Krai, Russia, situated on the Ob River and known as a local industrial and transport center.
  • B. Iboropa-Akoko
    Iboropa-Akoko is a town in the Akoko area of Ondo State, southwestern Nigeria, known as one of the region’s notable local communities.
  • C. Igbesa
    Igbesa is a prominent town in Ogun State, Nigeria, known for its growing industrial presence and educational institutions.
  • D. Isiokpo
    Isiokpo is a town in Rivers State, Nigeria, known as an administrative and commercial center within the Ikwerre region.
  • E. Eziobodo
    Eziobodo is a community in southeastern Nigeria located within the Owerri West Local Government Area of Imo State.
  • 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: Akassa (Ijo)
Triple: [Akassa language, hasAlternativeName, Akassa (Ijo)]
Generated description
Akassa (Ijo) is an endangered Ijoid language spoken by the Akassa people in the Niger Delta region of southern Nigeria.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Akassa (Ijo)
Target entity description: Akassa (Ijo) is an endangered Ijoid language spoken by the Akassa people in the Niger Delta region of southern Nigeria.
  • A. Kamen-na-Obi
    Kamen-na-Obi is a town in Altai Krai, Russia, situated on the Ob River and known as a local industrial and transport center.
  • B. Iboropa-Akoko
    Iboropa-Akoko is a town in the Akoko area of Ondo State, southwestern Nigeria, known as one of the region’s notable local communities.
  • C. Igbesa
    Igbesa is a prominent town in Ogun State, Nigeria, known for its growing industrial presence and educational institutions.
  • D. Isiokpo
    Isiokpo is a town in Rivers State, Nigeria, known as an administrative and commercial center within the Ikwerre region.
  • E. Eziobodo
    Eziobodo is a community in southeastern Nigeria located within the Owerri West Local Government Area of Imo State.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b033d6b88190a1366a58d63b0546 completed April 18, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a531ea7c81908630f16f6c685d49 completed May 10, 2026, 3:33 p.m.
NEDg Description generation batch_6a00a5b3ce848190a73f06d9708bfc85 completed May 10, 2026, 3:35 p.m.
NED2 Entity disambiguation (via description) batch_6a00a6734d008190bb0a5aa28826e73a completed May 10, 2026, 3:38 p.m.
Created at: April 10, 2026, 5:21 a.m.