Triple

T22893047
Position Surface form Disambiguated ID Type / Status
Subject Canaan Banana E568092 entity
Predicate spouse P13 FINISHED
Object Janet Banana 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: Janet Banana | Statement: [Canaan Banana, spouse, Janet Banana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Janet Banana
Context triple: [Canaan Banana, spouse, Janet Banana]
  • A. Janet Banana chosen
    Janet Banana was the wife of Zimbabwe’s first president, Canaan Banana, and served as the country’s inaugural First Lady after independence.
  • B. Janet
    Janet is a feminine given name commonly used in English-speaking countries, often associated with notable figures in entertainment and public life.
  • C. Jannetje
    Jannetje is the given name of Dutch World War II resistance fighter Hannie Schaft, a national heroine known as “the girl with the red hair.”
  • D. Djanet
    Djanet is an oasis town in southeastern Algeria, known for its prehistoric rock art, dramatic Sahara landscapes, and role as a gateway to the Tassili n'Ajjer plateau.
  • E. Banana West
    Banana West is a rural locality within Queensland’s Banana Shire, known primarily for its agricultural landscape and small-community character.
  • 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_69e2458c23ec81908fa2570692c6614f completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f17fc66dbc81909b31c068d7f2c531 completed April 29, 2026, 3:49 a.m.
Created at: April 17, 2026, 3:40 p.m.