Triple

T11258870
Position Surface form Disambiguated ID Type / Status
Subject Sandton E266508 entity
Predicate shoppingCentre P16039 FINISHED
Object Mall of Africa E323436 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: Mall of Africa | Statement: [Sandton, shoppingCentre, Mall of Africa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mall of Africa
Context triple: [Sandton, shoppingCentre, Mall of Africa]
  • A. Mall of Africa chosen
    Mall of Africa is one of the largest shopping malls in Africa, a major retail and entertainment destination located in Midrand, South Africa.
  • B. Morocco Mall
    Morocco Mall is one of Africa’s largest shopping and entertainment centers, located on the Atlantic coast in Casablanca and featuring international brands, dining, and leisure attractions.
  • C. Afula Illit Mall
    Afula Illit Mall is a major commercial shopping center serving as a key retail and social hub for residents of Afula and the surrounding area in northern Israel.
  • D. Kejetia Market
    Kejetia Market is one of West Africa’s largest open-air markets, a bustling commercial hub in Kumasi known for its dense maze of stalls and vibrant local trade.
  • E. Ibn Battuta Mall
    Ibn Battuta Mall is a large themed shopping and entertainment complex in Dubai, United Arab Emirates, inspired by the travels of the explorer Ibn Battuta.
  • 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_69d6aac7953c8190b82caf9d7640fdf9 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e936cb048190b4d6fb2851ef8932 completed April 9, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4ccada158819080e49833e09f84a0 completed April 19, 2026, 12:38 p.m.
Created at: April 8, 2026, 9:31 p.m.