Triple

T19935486
Position Surface form Disambiguated ID Type / Status
Subject Lupita Nyong'o E479163 entity
Predicate notableWork P4 FINISHED
Object Eclipsed 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: Eclipsed | Statement: [Lupita Nyong'o, notableWork, Eclipsed]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eclipsed
Context triple: [Lupita Nyong'o, notableWork, Eclipsed]
  • A. Eclipsed chosen
    Eclipsed is a critically acclaimed play by Danai Gurira that portrays the lives of women held captive during the Liberian Civil War.
  • B. Eclipsed
    Eclipsed is a comedic novel by British writer and comedian Dominic Holland, known for its humorous take on fame, family, and everyday life.
  • C. She Darked the Sun
    "She Darked the Sun" is a country-rock song by Dillard & Clark, featured on their influential late-1960s album The Fantastic Expedition of Dillard & Clark.
  • D. Two Moons
    Two Moons was a Northern Cheyenne chief and war leader known for his role in several key conflicts of the Great Sioux War of 1876–77, including the Battle of the Little Bighorn.
  • E. Full Dark, No Stars
    Full Dark, No Stars is a collection of four novellas by Stephen King that explore themes of revenge, guilt, and the darker sides of human nature.
  • 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a173a448190a25cb859803e3afc completed April 20, 2026, 4:53 p.m.
Created at: April 10, 2026, 1:53 p.m.