Triple

T14839773
Position Surface form Disambiguated ID Type / Status
Subject Darrell Roodt E348928 entity
Predicate notableWork P4 FINISHED
Object Sarafina! 2 E62321 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: Sarafina! 2 | Statement: [Darrell Roodt, notableWork, Sarafina! 2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarafina! 2
Context triple: [Darrell Roodt, notableWork, Sarafina! 2]
  • A. Sarafina! chosen
    Sarafina! is a 1992 South African musical drama film about a young girl’s coming-of-age during the Soweto uprising against apartheid.
  • B. Fataleka
    Fataleka is an Oceanic language of the Southeast Solomonic group spoken by the Fataleka people in the Solomon Islands.
  • C. Fanaa
    Fanaa is a 2006 Indian romantic thriller film that blends love and terrorism, starring Aamir Khan and Kajol.
  • D. Tareeno
    Tareeno is an alternative name for Wanetsi, an Eastern Iranian language closely related to Pashto and spoken primarily in parts of Pakistan and Afghanistan.
  • E. Serving Sara
    Serving Sara is a 2002 romantic comedy film starring Elizabeth Hurley and Matthew Perry, centered on a process server whose job goes awry when he helps the woman he's supposed to serve.
  • 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_69d822ec69008190a9232caa68836872 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded28e40f08190b309d8ac6404d2fc completed April 14, 2026, 11:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe38a9eb9481908ca509f484007cf6 completed May 8, 2026, 7:25 p.m.
Created at: April 10, 2026, 1:53 a.m.