Triple

T19400955
Position Surface form Disambiguated ID Type / Status
Subject Ginger E485321 entity
Predicate hasFriend P8712 FINISHED
Object Jezanna 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: Jezanna | Statement: [Ginger, hasFriend, Jezanna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jezanna
Context triple: [Ginger, hasFriend, Jezanna]
  • A. Jezanna chosen
    Jezanna is a recurring character in Alison Bechdel’s comic strip "Dykes to Watch Out For," known as one of the lesbian women whose personal and political life is explored in the series.
  • B. Zella
    Zella is an activewear and athleisure clothing brand known for its performance-focused yet stylish designs, sold at Nordstrom.
  • C. Janna
    Janna is an American tax attorney best known as the wife of former U.S. Speaker of the House and 2012 vice-presidential nominee Paul Ryan.
  • D. Jorja
    Jorja is a feminine given name most notably associated with American actress Jorja Fox.
  • E. Dilana
    Dilana is a South African-born rock singer and songwriter who gained international recognition as a standout contestant on the reality TV show "Rock Star: Supernova."
  • 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_69d8e8d5162481909db12435d9535c1a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62577454c81909d5bcd07e99b27e4 completed April 20, 2026, 1:09 p.m.
Created at: April 10, 2026, 1:36 p.m.