Triple

T16721798
Position Surface form Disambiguated ID Type / Status
Subject John Nathan-Turner E406364 entity
Predicate introducedCompanion P22642 FINISHED
Object Tegan Jovanka E378477 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: Tegan Jovanka | Statement: [John Nathan-Turner, introducedCompanion, Tegan Jovanka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tegan Jovanka
Context triple: [John Nathan-Turner, introducedCompanion, Tegan Jovanka]
  • A. Tegan Jovanka chosen
    Tegan Jovanka is a brash, outspoken Australian airline stewardess who serves as one of the Fifth Doctor’s companions in the classic British science fiction series Doctor Who.
  • B. Tegan West
    Tegan West is an American actor and screenwriter best known for his role in the Vietnam War film "Hamburger Hill" and for co-writing several film and television projects.
  • C. Tegan Quin
    Tegan Quin is a Canadian singer-songwriter best known as one half of the indie pop duo Tegan and Sara.
  • D. Leigh Nash
    Leigh Nash is an American singer and songwriter best known as the lead vocalist of the alternative pop band Sixpence None the Richer.
  • E. Tilly Grosser
    Tilly Grosser was the first wife of Austrian neurologist and Holocaust survivor Viktor Frankl, who perished during the Holocaust.
  • 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_69d8838f242881908abd8bc138795886 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e38743750c81908a980372ad8f1a6a completed April 18, 2026, 1:29 p.m.
NED1 Entity disambiguation (via context triple) batch_6a009d41cb6c8190bfa164ad20f009d9 completed May 10, 2026, 2:59 p.m.
Created at: April 10, 2026, 5:20 a.m.