Triple

T18926092
Position Surface form Disambiguated ID Type / Status
Subject Charles Logan E462973 entity
Predicate enemy P4567 FINISHED
Object Martha Logan 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: Martha Logan | Statement: [Charles Logan, enemy, Martha Logan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martha Logan
Context triple: [Charles Logan, enemy, Martha Logan]
  • A. Martha Logan chosen
    Martha Logan is a fictional First Lady of the United States on the television series "24," known for her troubled marriage to President Charles Logan and her moral opposition to his corrupt actions.
  • B. Mildred Washington
    Mildred Washington was an early 20th-century African American stage and film actress known for her performances during the Harlem Renaissance era.
  • C. Martha Martin
    Martha Martin was the first wife of prominent 19th-century American politician and senator Stephen A. Douglas.
  • D. Beth Grant
    Beth Grant is an American character actress known for her prolific work in film and television, often portraying strict, eccentric, or morally rigid supporting characters.
  • E. Laura Dearborn
    Laura Dearborn is a central character in Frank Norris’s novel "The Pit," portrayed as a cultured young woman whose romantic and moral struggles unfold against the backdrop of Chicago’s speculative wheat market.
  • 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_69d8dcfdbbb881909964fa5a75bd0b48 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c9b94e008190a0e9a70aaf6d18ed completed April 20, 2026, 6:37 a.m.
Created at: April 10, 2026, 11:59 a.m.