Triple

T6214879
Position Surface form Disambiguated ID Type / Status
Subject John W. Cahn E138960 entity
Predicate coAuthor P398 FINISHED
Object Pierre Haasen
Pierre Haasen was a German physicist and materials scientist known for his influential work on the physical metallurgy and plastic deformation of metals and alloys.
 E598588 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: Pierre Haasen | Statement: [John W. Cahn, coAuthor, Pierre Haasen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pierre Haasen
Context triple: [John W. Cahn, coAuthor, Pierre Haasen]
  • A. Michel Hofman
    Michel Hofman is a Belgian military officer who serves as the country's Chief of Defence, the highest-ranking position in the Belgian Armed Forces.
  • B. Charles Jonnart
    Charles Jonnart was a French politician and statesman of the Third Republic, known for his ministerial roles and influence in centrist republican politics.
  • C. Paul Thiry
    Paul Thiry was a prominent mid-20th-century American architect known as a leading figure of Northwest modernism.
  • D. Michel Harmand
    Michel Harmand is an automotive designer best known for his work on the innovative and aerodynamically styled Citroën CX.
  • E. Pierre Frank
    Pierre Frank was a French Trotskyist revolutionary and theorist who became a leading figure in the international Trotskyist movement.
  • 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: Pierre Haasen
Triple: [John W. Cahn, coAuthor, Pierre Haasen]
Generated description
Pierre Haasen was a German physicist and materials scientist known for his influential work on the physical metallurgy and plastic deformation of metals and alloys.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pierre Haasen
Target entity description: Pierre Haasen was a German physicist and materials scientist known for his influential work on the physical metallurgy and plastic deformation of metals and alloys.
  • A. Michel Hofman
    Michel Hofman is a Belgian military officer who serves as the country's Chief of Defence, the highest-ranking position in the Belgian Armed Forces.
  • B. Charles Jonnart
    Charles Jonnart was a French politician and statesman of the Third Republic, known for his ministerial roles and influence in centrist republican politics.
  • C. Paul Thiry
    Paul Thiry was a prominent mid-20th-century American architect known as a leading figure of Northwest modernism.
  • D. Michel Harmand
    Michel Harmand is an automotive designer best known for his work on the innovative and aerodynamically styled Citroën CX.
  • E. Pierre Frank
    Pierre Frank was a French Trotskyist revolutionary and theorist who became a leading figure in the international Trotskyist movement.
  • 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_69c008ada364819096c9e92c74d639b5 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062a0e0488190b71b42386bacf982 completed March 22, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69c67c36eac4819095b6a2b9e8a277f0 completed March 27, 2026, 12:46 p.m.
NEDg Description generation batch_69c67d8ce4f081908c95cfcdd690861c completed March 27, 2026, 12:52 p.m.
NED2 Entity disambiguation (via description) batch_69c67df2fb2081909ea5739efaa86770 completed March 27, 2026, 12:54 p.m.
Created at: March 22, 2026, 4:21 p.m.