Triple

T13550390
Position Surface form Disambiguated ID Type / Status
Subject Rose Ross E323628 entity
Predicate portrayedBy P1507 FINISHED
Object Caren Pistorius E323625 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: Caren Pistorius | Statement: [Rose Ross, portrayedBy, Caren Pistorius]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caren Pistorius
Context triple: [Rose Ross, portrayedBy, Caren Pistorius]
  • A. Caren Pistorius chosen
    Caren Pistorius is a South African-born New Zealand actress known for her roles in films such as the western thriller "Slow West" and the action thriller "Unhinged."
  • B. Elize Botha
    Elize Botha was the wife of former South African State President P. W. Botha and served as the country’s First Lady during his tenure.
  • C. Jopie Fourie
    Jopie Fourie was a South African Boer rebel and national figure executed during World War I for leading an armed uprising against the Union government.
  • D. Bridgette Radebe
    Bridgette Radebe is a South African mining entrepreneur and businesswoman, recognized as one of the country’s first black female mine owners and a prominent figure in the mining industry.
  • E. Angie Kruger
    Angie Kruger is known as the daughter of longtime college basketball coach Lon Kruger.
  • 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaff0a6548190b8cde5084cef0061 completed April 12, 2026, 2:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f76bb0195c8190b62e7aad4d78f899 completed May 3, 2026, 3:37 p.m.
Created at: April 9, 2026, 9:46 p.m.