Triple

T6334115
Position Surface form Disambiguated ID Type / Status
Subject Bill Irwin E142448 entity
Predicate spouse P13 FINISHED
Object Martha Roth
Martha Roth is the wife of American actor and clown Bill Irwin.
E597922 NE FINISHED

How this triple was built (4 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 Roth | Statement: [Bill Irwin, spouse, Martha Roth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martha Roth
Context triple: [Bill Irwin, spouse, Martha Roth]
  • A. Lillian Roth
    Lillian Roth was an American singer and stage and screen actress known for her early success in Hollywood musicals and her later public struggle with alcoholism and recovery.
  • B. Marion Rothman
    Marion Rothman was an American film editor known for her work on notable films of the 1960s and 1970s, including the crime thriller "The Boston Strangler."
  • C. Fannie Cohn
    Fannie Cohn was a prominent labor organizer and leader in the American garment industry, known for her influential role in advancing workers’ rights through the International Ladies' Garment Workers' Union.
  • D. Martha Schmellinsky
    Martha Schmellinsky was the wife of East German leader Walter Ulbricht and thus part of the political elite of the German Democratic Republic.
  • E. Ruth Wenger
    Ruth Wenger was a Swiss singer and writer best known for her brief marriage to Nobel Prize–winning author Hermann Hesse.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Martha Roth
Triple: [Bill Irwin, spouse, Martha Roth]
Generated description
Martha Roth is the wife of American actor and clown Bill Irwin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Martha Roth
Target entity description: Martha Roth is the wife of American actor and clown Bill Irwin.
  • A. Lillian Roth
    Lillian Roth was an American singer and stage and screen actress known for her early success in Hollywood musicals and her later public struggle with alcoholism and recovery.
  • B. Marion Rothman
    Marion Rothman was an American film editor known for her work on notable films of the 1960s and 1970s, including the crime thriller "The Boston Strangler."
  • C. Fannie Cohn
    Fannie Cohn was a prominent labor organizer and leader in the American garment industry, known for her influential role in advancing workers’ rights through the International Ladies' Garment Workers' Union.
  • D. Martha Schmellinsky
    Martha Schmellinsky was the wife of East German leader Walter Ulbricht and thus part of the political elite of the German Democratic Republic.
  • E. Ruth Wenger
    Ruth Wenger was a Swiss singer and writer best known for her brief marriage to Nobel Prize–winning author Hermann Hesse.
  • F. None of above. chosen

Provenance (5 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_69c008d4d8e88190ad301c05b08722ac completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06549084c8190b73fd94c9e0cb302 completed March 22, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69c66376b63081909fefd93790fa4b55 completed March 27, 2026, 11:01 a.m.
NEDg Description generation batch_69c664b2d44c8190826449707fe5ba7b completed March 27, 2026, 11:06 a.m.
NED2 Entity disambiguation (via description) batch_69c6650d676881908501874f1fd8c3df completed March 27, 2026, 11:07 a.m.
Created at: March 22, 2026, 4:30 p.m.