Triple

T19034988
Position Surface form Disambiguated ID Type / Status
Subject Hilary Majewski E465843 entity
Predicate name P16 FINISHED
Object Hilary Majewski 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: Hilary Majewski | Statement: [Hilary Majewski, name, Hilary Majewski]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hilary Majewski
Context triple: [Hilary Majewski, name, Hilary Majewski]
  • A. Hilary Majewski chosen
    Hilary Majewski was a prominent 19th-century Polish architect known for shaping the urban landscape of Łódź with grand eclectic and neo-Renaissance buildings.
  • B. Hilary Shor
    Hilary Shor is a film producer best known for her work on acclaimed features such as the dystopian drama "Children of Men."
  • C. Jennifer Hirsch
    Jennifer Hirsch is known as the sister of American actor Emile Hirsch.
  • D. Celeste Ackelson
    Celeste Ackelson is an American public relations professional best known as the wife of actor Brian Baumgartner, who played Kevin Malone on the U.S. version of "The Office."
  • E. Kathryn Chetkovich
    Kathryn Chetkovich is an American writer and essayist known for her fiction and for her widely discussed essay about envy and literary success.
  • 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d74295b88190b1c4621735a06223 completed April 20, 2026, 7:35 a.m.
Created at: April 10, 2026, 12:02 p.m.