Triple

T20664696
Position Surface form Disambiguated ID Type / Status
Subject An American Tail E507853 entity
Predicate voiceActor P1507 FINISHED
Object Erica Yohn 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: Erica Yohn | Statement: [An American Tail, voiceActor, Erica Yohn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erica Yohn
Context triple: [An American Tail, voiceActor, Erica Yohn]
  • A. Erica Yohn chosen
    Erica Yohn was an American character actress known for her supporting roles in film and television from the 1970s through the 1990s.
  • B. Erica Hanson
    Erica Hanson is the wife of American actor and comedian Ike Barinholtz, known for maintaining a relatively private life outside of her husband's public career.
  • C. Erica Oyama
    Erica Oyama is an American screenwriter and producer best known for creating the web series "Burning Love" and writing for various film and television comedies.
  • D. Elissa Matsueda
    Elissa Matsueda is a screenwriter best known for her work on the 2018 ensemble comedy film "Dog Days."
  • E. Tanya Horie
    Tanya Horie is a comic book colorist known for her work on titles such as DC Comics' "Dial H."
  • 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_69e0b4c059bc81908ea762cd73ea4424 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b2f541bc8190ac7946b91647f2b0 completed April 20, 2026, 11:12 p.m.
Created at: April 16, 2026, 11:44 a.m.