Triple

T22047369
Position Surface form Disambiguated ID Type / Status
Subject Ruvuma Region E544796 entity
Predicate capital P234 FINISHED
Object Songea 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: Songea | Statement: [Ruvuma Region, capital, Songea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Songea
Context triple: [Ruvuma Region, capital, Songea]
  • A. Songea chosen
    Songea is a major town in southern Tanzania that serves as an important regional administrative and commercial center.
  • B. Songak
    Songak is the historical name of the Korean city now known as Kaesong, which was a prominent capital during the Goryeo dynasty.
  • C. Tambolaka
    Tambolaka is a town on the Indonesian island of Sumba that serves as an important local hub with an airport and access point for exploring the island.
  • D. Sofifi
    Sofifi is a small coastal town on Halmahera Island in eastern Indonesia that serves as the administrative center of North Maluku Province.
  • E. Gbarnga
    Gbarnga is a city in central Liberia that gained prominence as a stronghold and de facto capital for rebel forces during the First Liberian Civil War.
  • 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_69e11e32445c8190ab97089b48a130bb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12830c674819080254d77ee02bc9f completed April 28, 2026, 9:35 p.m.
Created at: April 16, 2026, 8:26 p.m.