Triple

T19895880
Position Surface form Disambiguated ID Type / Status
Subject Herschel Saltzman E478150 entity
Predicate familyName P18 FINISHED
Object Saltzman
Saltzman is a surname of likely Ashkenazi Jewish origin borne by various individuals across fields such as politics, academia, and the arts.
 E1401584 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: Saltzman | Statement: [Herschel Saltzman, familyName, Saltzman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Saltzman
Context triple: [Herschel Saltzman, familyName, Saltzman]
  • A. Geissman
    Geissman is a surname most notably associated with American jazz guitarist and composer Grant Geissman.
  • B. Lamont
    Lamont is a surname of Scottish origin borne by various notable individuals in politics, finance, academia, and the arts.
  • C. Lamont
    Lamont is an unincorporated community in Kern County, California, known primarily as an agricultural and residential area near Bakersfield.
  • D. Lindemann
    Lindemann is a German surname most notably associated with Ferdinand von Lindemann, the mathematician who proved that π is a transcendental number.
  • E. Gelbard
    Gelbard is the petitioner in the U.S. Supreme Court case Gelbard v. United States, which addressed issues related to grand jury proceedings and the use of illegally obtained evidence.
  • 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: Saltzman
Triple: [Herschel Saltzman, familyName, Saltzman]
Generated description
Saltzman is a surname of likely Ashkenazi Jewish origin borne by various individuals across fields such as politics, academia, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Saltzman
Target entity description: Saltzman is a surname of likely Ashkenazi Jewish origin borne by various individuals across fields such as politics, academia, and the arts.
  • A. Geissman
    Geissman is a surname most notably associated with American jazz guitarist and composer Grant Geissman.
  • B. Lamont
    Lamont is a surname of Scottish origin borne by various notable individuals in politics, finance, academia, and the arts.
  • C. Lamont
    Lamont is an unincorporated community in Kern County, California, known primarily as an agricultural and residential area near Bakersfield.
  • D. Lindemann
    Lindemann is a German surname most notably associated with Ferdinand von Lindemann, the mathematician who proved that π is a transcendental number.
  • E. Gelbard
    Gelbard is the petitioner in the U.S. Supreme Court case Gelbard v. United States, which addressed issues related to grand jury proceedings and the use of illegally obtained evidence.
  • 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_69d8e520682081909892916424699bd5 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6593cb45881909cc34a9c601db001 completed April 20, 2026, 4:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07ea4027c081909f3e67f3f5dda46a completed May 16, 2026, 3:53 a.m.
NEDg Description generation batch_6a07ebef0a088190996451d7c0fdb013 completed May 16, 2026, 4 a.m.
NED2 Entity disambiguation (via description) batch_6a07ecb5ec708190bc79a1be73f746d9 completed May 16, 2026, 4:04 a.m.
Created at: April 10, 2026, 1:52 p.m.