Triple

T11426695
Position Surface form Disambiguated ID Type / Status
Subject Nehemiah Persoff E270769 entity
Predicate familyName P18 FINISHED
Object Persoff
Persoff is a surname most notably associated with Nehemiah Persoff, an American character actor known for his extensive work in film, television, and theater in the mid-20th century.
 E924807 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: Persoff | Statement: [Nehemiah Persoff, familyName, Persoff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Persoff
Context triple: [Nehemiah Persoff, familyName, Persoff]
  • A. Peretz
    Peretz is a Jewish surname most famously associated with I. L. Peretz, a seminal Yiddish and Hebrew writer of the late 19th and early 20th centuries.
  • B. Joffe
    Joffe is a surname most notably associated with Adolf Joffe, a prominent early 20th-century Russian revolutionary and diplomat.
  • C. Tobolowsky
    Tobolowsky is the surname of American character actor and storyteller Stephen Tobolowsky, known for his prolific work in film and television.
  • D. Pessin
    Pessin is a small municipality in the Havelland district of the German federal state of Brandenburg.
  • E. Gershon Kekst
    Gershon Kekst was a prominent American businessman and philanthropist known for his leadership in corporate communications and his significant support of Jewish and higher education institutions.
  • 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: Persoff
Triple: [Nehemiah Persoff, familyName, Persoff]
Generated description
Persoff is a surname most notably associated with Nehemiah Persoff, an American character actor known for his extensive work in film, television, and theater in the mid-20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Persoff
Target entity description: Persoff is a surname most notably associated with Nehemiah Persoff, an American character actor known for his extensive work in film, television, and theater in the mid-20th century.
  • A. Peretz
    Peretz is a Jewish surname most famously associated with I. L. Peretz, a seminal Yiddish and Hebrew writer of the late 19th and early 20th centuries.
  • B. Joffe
    Joffe is a surname most notably associated with Adolf Joffe, a prominent early 20th-century Russian revolutionary and diplomat.
  • C. Tobolowsky
    Tobolowsky is the surname of American character actor and storyteller Stephen Tobolowsky, known for his prolific work in film and television.
  • D. Pessin
    Pessin is a small municipality in the Havelland district of the German federal state of Brandenburg.
  • E. Gershon Kekst
    Gershon Kekst was a prominent American businessman and philanthropist known for his leadership in corporate communications and his significant support of Jewish and higher education institutions.
  • 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_69d6aadeef688190874bcecd88b3dd9b completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d806c000b88190bfaa646b2dc424b7 completed April 9, 2026, 8:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5b8c8e1988190aba5a2536dbb37cf completed April 20, 2026, 5:25 a.m.
NEDg Description generation batch_69e5c28e2dd481909b45a43b5825f393 completed April 20, 2026, 6:07 a.m.
NED2 Entity disambiguation (via description) batch_69e5c4722c348190a4c49edb1f6df240 completed April 20, 2026, 6:15 a.m.
Created at: April 8, 2026, 9:35 p.m.