Triple

T11894878
Position Surface form Disambiguated ID Type / Status
Subject Zeppo Marx E283009 entity
Predicate spouse P13 FINISHED
Object Barbara Marx E263593 NE FINISHED

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: Barbara Marx | Statement: [Zeppo Marx, spouse, Barbara Marx]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barbara Marx
Context triple: [Zeppo Marx, spouse, Barbara Marx]
  • A. Barbara Marx chosen
    Barbara Marx was an American model and socialite best known as the fourth and final wife of singer Frank Sinatra.
  • B. Barbara Blomberg
    Barbara Blomberg was a 16th-century German woman best known as the mistress of Holy Roman Emperor Charles V and the mother of his illegitimate son, John of Austria (the Elder).
  • C. Barbara Fuchs
    Barbara Fuchs is a literary scholar known for her work on early modern Spanish and English literature, translation, and cultural exchange.
  • D. Margaret Shenberg
    Margaret Shenberg was the first wife of influential Hollywood film producer and studio executive Louis B. Mayer.
  • E. 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.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6ab2a90b08190a4e818821cc93e6d completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8dd1286808190949719f54ff49a01 completed April 10, 2026, 11:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69f6d5e2b0408190866bbe9a3a56928b completed May 3, 2026, 4:58 a.m.
Created at: April 8, 2026, 9:44 p.m.