Triple

T21330494
Position Surface form Disambiguated ID Type / Status
Subject Eleanor Iselin E525884 entity
Predicate spouse P13 FINISHED
Object Senator John Iselin 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: Senator John Iselin | Statement: [Eleanor Iselin, spouse, Senator John Iselin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Senator John Iselin
Context triple: [Eleanor Iselin, spouse, Senator John Iselin]
  • A. Senator John Iselin chosen
    Senator John Iselin is a demagogic, McCarthy-like U.S. senator and primary antagonist in the 1962 political thriller "The Manchurian Candidate."
  • B. Senator Robert Lipton
    Senator Robert Lipton is a fictional Pennsylvania state senator and love interest of Angela Martin on the U.S. television series "The Office."
  • C. Thomas A. Burke
    Thomas A. Burke was a prominent Cleveland political figure who served as mayor and later as a U.S. senator from Ohio.
  • D. Charles Mathias
    Charles Mathias was a moderate Republican U.S. Senator from Maryland known for his independent stance on civil rights, opposition to the Vietnam War, and advocacy for government reform and oversight.
  • E. Senator Joseph Paine
    Senator Joseph Paine is a fictional, influential U.S. senator and key antagonist in the classic 1939 film "Mr. Smith Goes to Washington."
  • 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_69e0b51b90788190a4dd823d962626da completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7ab5177dc8190b888351e9a45b45f completed April 21, 2026, 4:52 p.m.
Created at: April 16, 2026, 4:42 p.m.