Triple

T6916978
Position Surface form Disambiguated ID Type / Status
Subject Abby Erceg E160082 entity
Predicate fullName P16 FINISHED
Object Abigail Erceg E160082 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: Abigail Erceg | Statement: [Abby Erceg, fullName, Abigail Erceg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Abigail Erceg
Context triple: [Abby Erceg, fullName, Abigail Erceg]
  • A. Abby Erceg chosen
    Abby Erceg is a New Zealand professional soccer defender and longtime national team captain known for her leadership and success in top women’s leagues, including the NWSL.
  • B. Erin Gerasimovich
    Erin Gerasimovich is an American child actress known for her role in the thriller film "Prisoners" and appearances in various television series.
  • C. Justine Ciarrocchi
    Justine Ciarrocchi is a film producer known for her work on contemporary American comedies such as "No Hard Feelings."
  • D. Abigail Adegboyega
    Abigail Adegboyega is the mother of British actor John Boyega, known for her Nigerian heritage and influence on his upbringing.
  • E. Libby Geist
    Libby Geist is an American documentary film producer best known for her work on acclaimed sports and social-issue documentaries, including the Oscar-winning "O.J.: Made in America."
  • 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_69c6883ab1008190a07129ff06f625d9 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6d9e034cc81908f1e8f31b055e119 completed March 27, 2026, 7:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7d36cc4048190b4ce8beb4c4f7957 completed March 28, 2026, 1:11 p.m.
Created at: March 27, 2026, 2:26 p.m.