Triple

T4356458
Position Surface form Disambiguated ID Type / Status
Subject Sergeant York E98158 entity
Predicate producer P490 FINISHED
Object Jesse L. Lasky E100728 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: Jesse L. Lasky | Statement: [Sergeant York, producer, Jesse L. Lasky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jesse L. Lasky
Context triple: [Sergeant York, producer, Jesse L. Lasky]
  • A. Jesse L. Lasky chosen
    Jesse L. Lasky was a pioneering American film producer and co-founder of Paramount Pictures who played a key role in the development of early Hollywood cinema.
  • B. Jesse L. Lasky Jr.
    Jesse L. Lasky Jr. was an American screenwriter known for his work on major Hollywood epics and adventure films in the mid-20th century.
  • C. Samuel Goldwyn
    Samuel Goldwyn was a pioneering American film producer and studio executive who played a key role in shaping Hollywood’s early motion picture industry.
  • D. Carl Laemmle
    Carl Laemmle was a pioneering German-American film producer and studio executive who founded Universal Pictures and helped shape the early Hollywood studio system.
  • E. Walter Wanger
    Walter Wanger was an American film producer known for his work on numerous influential Hollywood films from the 1930s through the 1950s, often tackling socially conscious and ambitious subjects.
  • 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_69b3454965f881908c41190bb22f0e4b completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b351c68a588190ba14a298afacb1dc completed March 12, 2026, 11:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5f5d00e20819095114787f95e3858 completed March 14, 2026, 11:57 p.m.
Created at: March 12, 2026, 11:16 p.m.