Triple

T14131602
Position Surface form Disambiguated ID Type / Status
Subject Paul Soros E350179 entity
Predicate founded P104 FINISHED
Object Sorost Company E1082017 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: Sorost Company | Statement: [Paul Soros, founded, Sorost Company]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sorost Company
Context triple: [Paul Soros, founded, Sorost Company]
  • A. Sorost Company chosen
    Sorost Company is a business enterprise associated with engineer and philanthropist Paul Soros, likely involved in engineering, shipping, or related industrial ventures.
  • B. United Company
    United Company was a prominent late 17th-century London theatre company formed by the merger of the King’s Company and the Duke’s Company, active during the Restoration period.
  • C. Peter Safran Company
    The Peter Safran Company is a film and television production company known for producing major Hollywood franchises, including DC superhero films like Aquaman.
  • D. Cantor Seinuk Group
    Cantor Seinuk Group was a prominent structural engineering firm known for its work on major high-rise and complex building projects, particularly in New York City.
  • E. Sosei Group Corporation
    Sosei Group Corporation is a Japan-based biopharmaceutical company that develops and acquires innovative drug discovery technologies and therapeutics through subsidiaries such as Heptares Therapeutics.
  • 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_69d827865f608190b311820428ae027b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de610cece88190b4a86500677e5938 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7e485fc8190aad0cce445aaec1a completed May 7, 2026, 8:36 p.m.
Created at: April 9, 2026, 11:16 p.m.