Triple

T9841420
Position Surface form Disambiguated ID Type / Status
Subject Heinrich Sahm E239234 entity
Predicate familyName P18 FINISHED
Object Sahm
Sahm is a German surname most notably borne by Heinrich Sahm, a prominent early 20th-century politician and mayor of Berlin.
 E825345 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: Sahm | Statement: [Heinrich Sahm, familyName, Sahm]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sahm
Context triple: [Heinrich Sahm, familyName, Sahm]
  • A. Arvin
    Arvin is a small agricultural city in Southern California’s San Joaquin Valley, known for its farming economy and diverse rural community.
  • B. Hagey
    Hagey is a surname most notably associated with Gerald Hagey, a prominent Canadian academic and founding president of the University of Waterloo.
  • C. O'Steen
    O'Steen is a surname most notably associated with American film editor Sam O'Steen, known for his work on several acclaimed Hollywood films.
  • D. Sandrich
    Sandrich is a surname most notably associated with American film director Mark Sandrich, known for his classic Hollywood musicals.
  • E. Sharman
    Sharman is a surname most notably associated with Helen Sharman, the first British astronaut and the first Western European woman in space.
  • 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: Sahm
Triple: [Heinrich Sahm, familyName, Sahm]
Generated description
Sahm is a German surname most notably borne by Heinrich Sahm, a prominent early 20th-century politician and mayor of Berlin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sahm
Target entity description: Sahm is a German surname most notably borne by Heinrich Sahm, a prominent early 20th-century politician and mayor of Berlin.
  • A. Arvin
    Arvin is a small agricultural city in Southern California’s San Joaquin Valley, known for its farming economy and diverse rural community.
  • B. Hagey
    Hagey is a surname most notably associated with Gerald Hagey, a prominent Canadian academic and founding president of the University of Waterloo.
  • C. O'Steen
    O'Steen is a surname most notably associated with American film editor Sam O'Steen, known for his work on several acclaimed Hollywood films.
  • D. Sandrich
    Sandrich is a surname most notably associated with American film director Mark Sandrich, known for his classic Hollywood musicals.
  • E. Sharman
    Sharman is a surname most notably associated with Helen Sharman, the first British astronaut and the first Western European woman in space.
  • 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_69ca84e3f0c48190ada72a65ebd50efd completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb34c920c81909b56ed9936b15f9b completed April 2, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1d5d9673c8190ada27bef9220798d completed April 5, 2026, 3:24 a.m.
NEDg Description generation batch_69d1d6815e28819081788393cda63bc0 completed April 5, 2026, 3:26 a.m.
NED2 Entity disambiguation (via description) batch_69d1d74e7a148190a9470745bfd7ad42 completed April 5, 2026, 3:30 a.m.
Created at: March 30, 2026, 8:33 p.m.