Triple

T16072749
Position Surface form Disambiguated ID Type / Status
Subject Marcus Goldman E389902 entity
Predicate employer P7 FINISHED
Object Goldman Sachs E145322 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: Goldman Sachs | Statement: [Marcus Goldman, employer, Goldman Sachs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Goldman Sachs
Context triple: [Marcus Goldman, employer, Goldman Sachs]
  • A. Goldman Sachs chosen
    Goldman Sachs is a leading global investment banking, securities, and asset management firm headquartered in New York City.
  • B. Morgan Stanley
    Morgan Stanley is a leading global financial services firm known for its investment banking, securities, wealth management, and investment management services.
  • C. Citigroup
    Citigroup is a major American multinational investment bank and financial services corporation headquartered in New York City.
  • D. Goldman
    Goldman is a surname most famously associated with Emma Goldman, the anarchist political activist and writer.
  • E. Credit Suisse
    Credit Suisse is a major global investment bank and financial services firm headquartered in Switzerland, known for its wealth management, investment banking, and asset management operations.
  • 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_6a006796bed4819085d988d7f2d7afcb completed May 10, 2026, 11:10 a.m.
Created at: April 10, 2026, 4:57 a.m.