Triple

T114160
Position Surface form Disambiguated ID Type / Status
Subject Primo Levi E2307 entity
Predicate familyName P18 FINISHED
Object Levi
Levi is the surname of Primo Levi, the renowned Italian Jewish chemist and writer best known for his memoirs about surviving the Auschwitz concentration camp.
 E11399 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: Levi | Statement: [Primo Levi, familyName, Levi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Levi
Context triple: [Primo Levi, familyName, Levi]
  • A. Samuel
    Samuel is the birth name of the famed American author Mark Twain, known for classics like "The Adventures of Tom Sawyer" and "Adventures of Huckleberry Finn."
  • B. Porter
    Porter is a transit station in Cambridge, Massachusetts that serves both MBTA commuter rail and Red Line subway services.
  • C. Holden
    Holden was an Australian automobile manufacturer and marque owned by General Motors, known for producing popular locally designed cars before ceasing operations in the 21st century.
  • D. Lee
    Lee is a given name shared by numerous individuals across different cultures and professions.
  • E. Bader
    Bader is the maiden surname of Ruth Bader Ginsburg, the late U.S. Supreme Court Justice and pioneering advocate for gender equality.
  • 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: Levi
Triple: [Primo Levi, familyName, Levi]
Generated description
Levi is the surname of Primo Levi, the renowned Italian Jewish chemist and writer best known for his memoirs about surviving the Auschwitz concentration camp.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Levi
Target entity description: Levi is the surname of Primo Levi, the renowned Italian Jewish chemist and writer best known for his memoirs about surviving the Auschwitz concentration camp.
  • A. Samuel
    Samuel is the birth name of the famed American author Mark Twain, known for classics like "The Adventures of Tom Sawyer" and "Adventures of Huckleberry Finn."
  • B. Porter
    Porter is a transit station in Cambridge, Massachusetts that serves both MBTA commuter rail and Red Line subway services.
  • C. Holden
    Holden was an Australian automobile manufacturer and marque owned by General Motors, known for producing popular locally designed cars before ceasing operations in the 21st century.
  • D. Lee
    Lee is a given name shared by numerous individuals across different cultures and professions.
  • E. Bader
    Bader is the maiden surname of Ruth Bader Ginsburg, the late U.S. Supreme Court Justice and pioneering advocate for gender equality.
  • 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_69a24fcdaeb48190a2d796677e4b3281 completed Feb. 28, 2026, 2:15 a.m.
NER Named-entity recognition batch_69a256effaac81908c22be65d9f668a4 completed Feb. 28, 2026, 2:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69a27c0652508190aa8d569ee7dae7bc completed Feb. 28, 2026, 5:24 a.m.
NEDg Description generation batch_69a27cc652048190bd6ac1fb6788991a completed Feb. 28, 2026, 5:27 a.m.
NED2 Entity disambiguation (via description) batch_69a27d8de2888190a9f37390d7a4324e completed Feb. 28, 2026, 5:30 a.m.
Created at: Feb. 28, 2026, 2:20 a.m.