Triple

T3612736
Position Surface form Disambiguated ID Type / Status
Subject Moshi E76525 entity
Predicate roadConnectionTo P9041 FINISHED
Object Tanga E374023 NE FINISHED

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: Tanga | Statement: [Moshi, roadConnectionTo, Tanga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tanga
Context triple: [Moshi, roadConnectionTo, Tanga]
  • A. Tanga Region chosen
    Tanga Region is a coastal administrative region in northeastern Tanzania known for its port city of Tanga, Indian Ocean shoreline, and proximity to the Usambara Mountains.
  • B. Takrur
    Takrur was an early West African kingdom located in the Senegal River valley, known for its role in trans-Saharan trade and its early adoption of Islam.
  • C. Bashenga
    Bashenga is a legendary Wakandan warrior and the first Black Panther, revered as the founder of the Panther cult and an ancestor of T'Challa in Marvel Comics.
  • D. Lunda
    Lunda is a Bantu language spoken primarily by the Lunda people in parts of Zambia, Angola, and the Democratic Republic of the Congo.
  • E. Mozambique
    Mozambique is a southeastern African nation on the Indian Ocean known for its Portuguese colonial heritage, rich cultural diversity, and extensive coastline with important ports and marine resources.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ad85da0ba481908b3b48c69efe2b98 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc2786f808190be4e42734a79d74e completed March 8, 2026, 6:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b44f068e188190bb8c4e098e3153b3 completed March 13, 2026, 5:53 p.m.
Created at: March 8, 2026, 3:23 p.m.