Triple

T20055462
Position Surface form Disambiguated ID Type / Status
Subject Peter Russo E499318 entity
Predicate hasAffairWith P23617 FINISHED
Object Rachel Posner 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: Rachel Posner | Statement: [Peter Russo, hasAffairWith, Rachel Posner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rachel Posner
Context triple: [Peter Russo, hasAffairWith, Rachel Posner]
  • A. Rachel Posner chosen
    Rachel Posner is a recurring character on the political drama series "House of Cards," known for her involvement in the Underwoods’ web of manipulation and corruption.
  • B. Rachel Leibowitz
    Rachel Leibowitz is a person notable enough to be specifically cited as a bearer of the surname Leibowitz.
  • C. Rachel Ellenstein
    Rachel Ellenstein is a key supporting character in the Highlander franchise, known as Connor MacLeod’s devoted adoptive daughter and confidante throughout his immortal life.
  • D. Jennifer Pozner
    Jennifer Pozner is a media critic, author, and founder of the advocacy group Women in Media & News, known for her feminist analysis of media representation and pop culture.
  • E. Sarah E. Reisman
    Sarah E. Reisman is an American organic chemist known for her work in complex natural product synthesis and as a professor at the California Institute of Technology.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66332b300819097f5dca1636e5822 completed April 20, 2026, 5:32 p.m.
Created at: April 11, 2026, 3:38 p.m.