Triple

T7714618
Position Surface form Disambiguated ID Type / Status
Subject Goodbye Bafana E174849 entity
Predicate mainSubject P3 FINISHED
Object Robben Island E23909 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: Robben Island | Statement: [Goodbye Bafana, mainSubject, Robben Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robben Island
Context triple: [Goodbye Bafana, mainSubject, Robben Island]
  • A. Robben Island chosen
    Robben Island is a historic island off the coast of Cape Town best known for housing the prison where Nelson Mandela and other anti-apartheid activists were incarcerated.
  • B. Victor Verster Prison
    Victor Verster Prison is a South African correctional facility best known as the place where Nelson Mandela spent the final years of his imprisonment before his release in 1990.
  • C. Bhisho
    Bhisho is a small administrative town in South Africa that serves as the political and governmental center of the Eastern Cape province.
  • D. Krugersdorp Prison
    Krugersdorp Prison is a correctional facility located in the town of Krugersdorp in Gauteng, South Africa, used for the incarceration and rehabilitation of offenders.
  • E. Maputo Fortress
    Maputo Fortress is a historic Portuguese-built military fort in Maputo, Mozambique, now serving as a cultural and tourist attraction.
  • 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_69c6995c463c8190a14458036249d419 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c702ca8f048190a6ea27b8cee2f93e completed March 27, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8acd5e32c8190869834b21aeae8a7 completed March 29, 2026, 4:38 a.m.
Created at: March 27, 2026, 4:04 p.m.