Triple

T16072747
Position Surface form Disambiguated ID Type / Status
Subject Marcus Goldman E389902 entity
Predicate relative P37 FINISHED
Object Samuel Sachs E387201 NE FINISHED

How this triple was built (2 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: Samuel Sachs | Statement: [Marcus Goldman, relative, Samuel Sachs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samuel Sachs
Context triple: [Marcus Goldman, relative, Samuel Sachs]
  • A. Samuel Sachs chosen
    Samuel Sachs was an American investment banker whose partnership helped transform Goldman Sachs into a leading global financial institution in the late 19th and early 20th centuries.
  • B. Samuel Lipman
    Samuel Lipman was one of the Russian-born Jewish anarchists prosecuted in the 1919 U.S. Supreme Court case Abrams v. United States for distributing anti-war leaflets during World War I.
  • C. Samuel Weiss
    Samuel Weiss is a relatively obscure individual whose specific public significance is not clearly established from the available information.
  • D. Samuel Baum
    Samuel Baum is a television writer and producer best known for creating the crime drama series "Lie to Me."
  • E. Samuel A. Marx
    Samuel A. Marx was an American architect and designer known for his modernist buildings and influential work in mid-20th-century commercial and residential architecture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e183bf6c488190b0099a00f13f2a69 completed April 17, 2026, 12:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe484cef08190a3797c91a7025081 completed May 10, 2026, 1:51 a.m.
Created at: April 10, 2026, 4:57 a.m.