Triple

T10176429
Position Surface form Disambiguated ID Type / Status
Subject Charles Longuet E235863 entity
Predicate relative P37 FINISHED
Object Laura Marx E363608 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: Laura Marx | Statement: [Charles Longuet, relative, Laura Marx]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laura Marx
Context triple: [Charles Longuet, relative, Laura Marx]
  • A. Laura Marx chosen
    Laura Marx was the daughter of philosopher Karl Marx and Jenny von Westphalen, known for her involvement in socialist and labor movements in the late 19th century.
  • B. Laura Jeanne
    Laura Jeanne is the birth name of American actress and producer Reese Witherspoon, known for films like "Legally Blonde" and "Walk the Line."
  • C. Julia Floyd
    Julia Floyd was the wife of British statesman Sir Robert Peel, serving as a prominent Victorian-era political hostess and member of the English gentry.
  • D. Mary Louise
    Mary Louise is the given first name of Irish politician Mary Lou McDonald, leader of the Sinn Féin party.
  • E. Sarah Fidel
    Sarah Fidel is a skilled and resourceful operative in the action-comedy film "Operation Fortune: Ruse de Guerre," known for her intelligence and crucial role within the espionage team.
  • 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_69ca84d1d5f88190ab878a1021ecff68 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdecd3a2688190bce277bffffcbf8b completed April 2, 2026, 4:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d301232e5c8190ad80c4e78681994c completed April 6, 2026, 12:41 a.m.
Created at: March 30, 2026, 9:11 p.m.