Triple

T8431003
Position Surface form Disambiguated ID Type / Status
Subject Queen Sugar E199112 entity
Predicate leadActor P1507 FINISHED
Object Kofi Siriboe E519699 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: Kofi Siriboe | Statement: [Queen Sugar, leadActor, Kofi Siriboe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kofi Siriboe
Context triple: [Queen Sugar, leadActor, Kofi Siriboe]
  • A. Kofi Siriboe chosen
    Kofi Siriboe is an American actor and model best known for his role as Ralph Angel Bordelon on the television series "Queen Sugar."
  • B. Franz Drameh
    Franz Drameh is a British actor known for roles in films like "Attack the Block" and "Edge of Tomorrow" and for playing Firestorm on the TV series "Legends of Tomorrow."
  • C. Kofi Mole
    Kofi Mole is a Ghanaian hip hop and afrobeat musician known for his energetic style and hit songs like "Don't Be Late."
  • D. Kwesi Adofo-Mensah
    Kwesi Adofo-Mensah is an NFL executive known for his analytics-driven approach to roster building as the general manager of the Minnesota Vikings.
  • E. Kofi Yamgnane
    Kofi Yamgnane is a Togolese-born French politician and civil engineer known for his work in local government and his role as a symbol of diversity in French politics.
  • 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_69ca8313c99081909a5c6d83b91de5b3 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbd1a4876c81908d5a708bb1f35683 completed March 31, 2026, 1:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce0380ed948190bdba247d67769ade completed April 2, 2026, 5:49 a.m.
Created at: March 30, 2026, 6:07 p.m.