Triple

T8367171
Position Surface form Disambiguated ID Type / Status
Subject Riaad Moosa E197157 entity
Predicate name P16 FINISHED
Object Riaad Moosa E197157 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: Riaad Moosa | Statement: [Riaad Moosa, name, Riaad Moosa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Riaad Moosa
Context triple: [Riaad Moosa, name, Riaad Moosa]
  • A. Riaad Moosa chosen
    Riaad Moosa is a South African comedian, actor, and medical doctor known for his stand-up comedy and roles in films and television.
  • B. Nasri Atweh
    Nasri Atweh is a Canadian singer-songwriter and producer best known as half of the pop duo Magic! and for writing and co-writing numerous hit songs for major artists.
  • C. Usmar Ismail
    Usmar Ismail was a pioneering Indonesian film director and producer, often regarded as the father of Indonesian cinema.
  • D. Sonallah Ibrahim
    Sonallah Ibrahim is a prominent Egyptian novelist and short story writer known for his politically charged, experimental works that critique authoritarianism and social injustice in the Arab world.
  • E. Mohammed Waheed Hassan
    Mohammed Waheed Hassan is a Maldivian politician who served as President of the Maldives following the resignation of Mohamed Nasheed.
  • 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_69ca82f2dbe48190aba982e75a0d94de completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb808cf80c8190941c3cc0248a5df2 completed March 31, 2026, 8:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69cdc78c0c208190ba590c74512a4043 completed April 2, 2026, 1:34 a.m.
Created at: March 30, 2026, 6 p.m.