Triple

T16047970
Position Surface form Disambiguated ID Type / Status
Subject Makhuwa people E389272 entity
Predicate countryMinority P65548 FINISHED
Object Tanzania E19037 NE FINISHED

How this triple was built (3 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: Tanzania | Statement: [Makhuwa people, countryMinority, Tanzania]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tanzania
Context triple: [Makhuwa people, countryMinority, Tanzania]
  • A. Tanzania chosen
    Tanzania is an East African nation known for its vast wilderness areas, including the Serengeti National Park and Mount Kilimanjaro, as well as its rich cultural diversity.
  • B. Tansaniaweg
    Tansaniaweg is a street in Berlin’s Afrikanisches Viertel, named in reference to the East African country Tanzania and its historical connections to Germany.
  • C. 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.
  • D. Tanzania and Burundi
    Tanzania and Burundi are neighboring East African countries that share a border along the eastern shore of Lake Tanganyika.
  • E. Malawi
    Malawi is a landlocked country in southeastern Africa known for Lake Malawi, its predominantly agricultural economy, and membership in regional and international organizations including the Commonwealth.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: countryMinority
Context triple: [Makhuwa people, countryMinority, Tanzania]
  • A. shareMinorityPopulations
    Indicates that two entities have overlapping or similar minority population groups in terms of presence, composition, or distribution.
  • B. minority chosen
    Indicates that one entity belongs to a smaller, less represented, or non-dominant group within a larger population or context.
  • C. alsoGovernsMinorities
    Indicates that the governing authority or body has jurisdiction or administrative responsibility not only over the primary population but also over minority groups within the same domain.
  • D. historicalMinority
    Indicates that an entity has been part of a group that has been numerically, politically, or socially subordinate within a society over a significant historical period.
  • E. languageMinorityGroupsDefinedBy
    Indicates that language minority groups are characterized or specified according to a particular criterion, classification, or defining attribute.
  • F. None of above.

Provenance (4 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_69d86dae698881908327ef2d67706cb9 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1858a00888190b8505071575dc56f completed April 17, 2026, 12:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbddc25481908fca660c4f14eaff completed May 10, 2026, 1:14 a.m.
PD Predicate disambiguation batch_69e18272f2288190a17d45fb01cc2b07 completed April 17, 2026, 12:44 a.m.
Created at: April 10, 2026, 4:56 a.m.