Triple

T14654980
Position Surface form Disambiguated ID Type / Status
Subject Plague of Frogs arc E344085 entity
Predicate mainCharacter P1183 FINISHED
Object Kate Corrigan E354738 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: Kate Corrigan | Statement: [Plague of Frogs arc, mainCharacter, Kate Corrigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Corrigan
Context triple: [Plague of Frogs arc, mainCharacter, Kate Corrigan]
  • A. Kate Corrigan chosen
    Kate Corrigan is a key human advisor and field coordinator in the Hellboy comics, serving as a scholar and senior operative within the Bureau for Paranormal Research and Defense.
  • B. Nadine Corrigan
    Nadine Corrigan is a fictional character from the crime novel "A Man Alone," involved in the story’s central mystery and interpersonal drama.
  • C. Kate Kavanagh
    Kate Kavanagh is a fictional character best known as Anastasia Steele’s outspoken journalist roommate and friend in the "Fifty Shades of Grey" series.
  • D. Kelly Corrigan
    Kelly Corrigan is an American author, memoirist, and podcast host known for her heartfelt reflections on family, illness, and resilience.
  • E. Mary Corrigan
    Mary Corrigan is known as the wife of British-born American semiconductor executive Wilfred Corrigan.
  • 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_69d822e1a2cc81908e5bb93cf61ce3cc completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb518f7dc8190877997ea4cd3eed2 completed April 14, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_6a003c405ecc81909722377a22db84a5 completed May 10, 2026, 8:05 a.m.
Created at: April 10, 2026, 1:27 a.m.