Triple

T19028089
Position Surface form Disambiguated ID Type / Status
Subject Bojanala Platinum District Municipality E465663 entity
Predicate hasMunicipalCode P3943 FINISHED
Object DC37 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: DC37 | Statement: [Bojanala Platinum District Municipality, hasMunicipalCode, DC37]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DC37
Context triple: [Bojanala Platinum District Municipality, hasMunicipalCode, DC37]
  • A. DC37 chosen
    DC37 is the official district code designating the Bojanala Platinum District in South Africa’s North West province.
  • B. DC34
    DC34 is the official municipal code assigned to the Vhembe District Municipality in South Africa.
  • C. DC31
    DC31 is the official municipal code assigned to the Nkangala District Municipality in South Africa’s Mpumalanga province.
  • D. DC35
    DC35 is the official municipal code designating the Capricorn District Municipality in South Africa’s Limpopo province.
  • E. DC39
    DC39 is the official administrative district code assigned to the Dr Ruth Segomotsi Mompati District in South Africa’s North West Province.
  • 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d73dc404819092059e496662d151 completed April 20, 2026, 7:35 a.m.
Created at: April 10, 2026, 12:02 p.m.