Triple

T22407622
Position Surface form Disambiguated ID Type / Status
Subject Half of a Yellow Sun E553917 entity
Predicate mainCharacter P1183 FINISHED
Object Richard NE NERFINISHED

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: Richard | Statement: [Half of a Yellow Sun, mainCharacter, Richard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard
Context triple: [Half of a Yellow Sun, mainCharacter, Richard]
  • A. Richard chosen
    Richard is a common masculine given name of Germanic origin, widely used in English-speaking countries.
  • B. Edward
    Edward is a masculine given name of English origin, historically associated with kings of England and notable figures such as U.S. Senator Edward M. Kennedy.
  • C. Richard the Good
    Richard the Good was a 10th–11th century Duke of Normandy known for consolidating Norman power in northern France and fostering the region’s political and religious development.
  • D. King Henry
    King Henry is a contemporary music producer known for his work in pop and electronic genres with major artists.
  • E. Charles
    Charles is a masculine given name of Germanic origin that has been widely used across Europe and the English-speaking world, borne by numerous historical figures, royalty, and notable individuals.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e4da7048190b4387d422a9a0de5 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158ba1c6481908e4b9b3635ed3a49 completed April 29, 2026, 1:02 a.m.
Created at: April 16, 2026, 8:46 p.m.