Triple

T8527399
Position Surface form Disambiguated ID Type / Status
Subject Erich von Manstein E201851 entity
Predicate familyName P18 FINISHED
Object von Lewinski E172511 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: von Lewinski | Statement: [Erich von Manstein, familyName, von Lewinski]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: von Lewinski
Context triple: [Erich von Manstein, familyName, von Lewinski]
  • A. von Lewinski chosen
    von Lewinski is a German noble family name historically associated with several Prussian military officers, including Field Marshal Erich von Manstein.
  • B. Nicki Lewinsky
    Nicki Lewinsky is one of Nicki Minaj’s provocative alter egos, often associated with her more sexually explicit and bold lyrical persona.
  • C. Monica Lewinsky
    Monica Lewinsky is an American activist, writer, and former White House intern best known for her involvement in a 1990s political scandal with President Bill Clinton and her later work against cyberbullying and public shaming.
  • D. Lew
    Lew is a surname most prominently associated with Jack Lew, the former U.S. Secretary of the Treasury.
  • E. Wojcicki
    Wojcicki is a Polish surname most prominently associated with Susan Wojcicki, the longtime former CEO of YouTube and an influential figure in the tech industry.
  • 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_69ca83228b24819085d22e7dc99f5d94 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe6477100819081fa20cb6b8ea3d7 completed March 31, 2026, 3:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce6d54ef908190970a1010c8018abd completed April 2, 2026, 1:21 p.m.
Created at: March 30, 2026, 6:16 p.m.