Triple

T4526013
Position Surface form Disambiguated ID Type / Status
Subject Agence France-Presse E103378 entity
Predicate hasOfficeIn P1268 FINISHED
Object Johannesburg E16031 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: Johannesburg | Statement: [Agence France-Presse, hasOfficeIn, Johannesburg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johannesburg
Context triple: [Agence France-Presse, hasOfficeIn, Johannesburg]
  • A. Johannesburg, South Africa chosen
    Johannesburg, South Africa is the country’s largest city and economic hub, known for its role in the gold mining industry and as a major urban center in Gauteng province.
  • B. Cape Town
    Cape Town is a major coastal city in South Africa known for its iconic Table Mountain, diverse culture, and role as the country’s legislative capital.
  • C. Tshwane
    Tshwane is a major metropolitan area in South Africa that includes the country’s administrative capital, Pretoria, and serves as an important political and economic hub.
  • D. Pretoria, South Africa
    Pretoria, South Africa is one of the country’s three capital cities, serving as the administrative capital and a major center for government, education, and culture.
  • E. Durban
    Durban is a major coastal city in South Africa known for its busy port, subtropical climate, and significant Indian community.
  • 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_69bd43dba59881908cf59b31df8c7ae1 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd577490f48190ac1fb3cbf3d8a41e completed March 20, 2026, 2:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69be6f8abc3481909dbb42ddde2729ca completed March 21, 2026, 10:14 a.m.
Created at: March 20, 2026, 1:03 p.m.