Triple

T2008913
Position Surface form Disambiguated ID Type / Status
Subject Out of Africa E43646 entity
Predicate mainCharacter P1183 FINISHED
Object Karen Blixen E226081 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: Karen Blixen | Statement: [Out of Africa, mainCharacter, Karen Blixen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karen Blixen
Context triple: [Out of Africa, mainCharacter, Karen Blixen]
  • A. Karen Blixen chosen
    Karen Blixen, also known by her pen name Isak Dinesen, was a Danish author renowned for her memoirs and stories set in colonial Kenya, most famously "Out of Africa."
  • B. Birgitta Dahl
    Birgitta Dahl is a Swedish Social Democratic politician who served as Speaker of the Riksdag and was a prominent figure in Sweden’s late 20th-century political landscape.
  • C. Sigrid Undset
    Sigrid Undset was a Norwegian novelist and Nobel Prize in Literature laureate best known for her medieval trilogy "Kristin Lavransdatter."
  • D. Frances Kuper
    Frances Kuper is known as a former spouse of investigative journalist and author Bob Woodward.
  • E. Astrid Lindley
    Astrid Lindley is known as the wife of late Pro Football Hall of Famer and broadcaster Frank Gifford.
  • 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_69a88716e9f08190946313fdc949e3cf completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb89be08c81909eb5ea672ea46b2b completed March 7, 2026, 5:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae1fe3480c8190add171121653fc8a completed March 9, 2026, 1:18 a.m.
Created at: March 4, 2026, 7:37 p.m.