Triple

T13542979
Position Surface form Disambiguated ID Type / Status
Subject Mall of Africa E323436 entity
Predicate hasAnchorTenant P11754 FINISHED
Object Edgars
Edgars is a major South African retail chain known primarily for selling fashion, beauty products, and household goods.
 E1046403 NE FINISHED

How this triple was built (4 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: Edgars | Statement: [Mall of Africa, hasAnchorTenant, Edgars]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Edgars
Context triple: [Mall of Africa, hasAnchorTenant, Edgars]
  • A. Burdine
    Burdine is the respondent in the U.S. Supreme Court employment discrimination case Texas Department of Community Affairs v. Burdine, which clarified the burden of proof framework in Title VII disparate treatment claims.
  • B. Webling
    Webling is a surname most notably associated with Peggy Webling, the British playwright and novelist known for her early stage adaptation of Mary Shelley's "Frankenstein."
  • C. Eisenberg
    Eisenberg is a surname most notably associated with American actress Hallie Kate Eisenberg.
  • D. Eisenberg
    Eisenberg is a small town in the German state of Thuringia that serves as an administrative and cultural center for its surrounding rural district.
  • E. Bonderman
    Bonderman is a surname most prominently associated with American billionaire investor and private equity pioneer David Bonderman.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Edgars
Triple: [Mall of Africa, hasAnchorTenant, Edgars]
Generated description
Edgars is a major South African retail chain known primarily for selling fashion, beauty products, and household goods.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Edgars
Target entity description: Edgars is a major South African retail chain known primarily for selling fashion, beauty products, and household goods.
  • A. Burdine
    Burdine is the respondent in the U.S. Supreme Court employment discrimination case Texas Department of Community Affairs v. Burdine, which clarified the burden of proof framework in Title VII disparate treatment claims.
  • B. Webling
    Webling is a surname most notably associated with Peggy Webling, the British playwright and novelist known for her early stage adaptation of Mary Shelley's "Frankenstein."
  • C. Eisenberg
    Eisenberg is a surname most notably associated with American actress Hallie Kate Eisenberg.
  • D. Eisenberg
    Eisenberg is a small town in the German state of Thuringia that serves as an administrative and cultural center for its surrounding rural district.
  • E. Bonderman
    Bonderman is a surname most prominently associated with American billionaire investor and private equity pioneer David Bonderman.
  • F. None of above. chosen

Provenance (5 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafda36248190acabde65a88c5471 completed April 12, 2026, 2:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75da094288190aff108b006c3da1f completed May 3, 2026, 2:37 p.m.
NEDg Description generation batch_69f75f2c645481909c3e5ecdd239965d completed May 3, 2026, 2:43 p.m.
NED2 Entity disambiguation (via description) batch_69f75f8e9b608190830ab942098a798c completed May 3, 2026, 2:45 p.m.
Created at: April 9, 2026, 9:45 p.m.