Triple

T18906220
Position Surface form Disambiguated ID Type / Status
Subject Chamwino State House, Dodoma E462469 entity
Predicate associatedWith P37 FINISHED
Object Ikulu 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: Ikulu | Statement: [Chamwino State House, Dodoma, associatedWith, Ikulu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ikulu
Context triple: [Chamwino State House, Dodoma, associatedWith, Ikulu]
  • A. Ikulu chosen
    Ikulu is the presidential residence and official State House of Tanzania, located in Dar es Salaam.
  • B. Ikela
    Ikela is a town in the Democratic Republic of the Congo situated in the central rainforest region and historically known as an administrative and trading center.
  • C. Kika
    Kika is a song that follows "High Heels" in a music release sequence, likely within the pop or dance genre.
  • D. Kika
    Kika is a common diminutive or nickname for the female given name Kristina.
  • E. Kalunga
    Kalunga is a central supreme deity in the traditional religion of the Ovambo people of southern Africa, associated with creation, destiny, and the boundary between life and death.
  • 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_69d8dcfd05bc819088903cca13cc2846 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c52cc9cc8190ac489d36e51693c8 completed April 20, 2026, 6:18 a.m.
Created at: April 10, 2026, 11:58 a.m.