Triple

T1108769
Position Surface form Disambiguated ID Type / Status
Subject Greta Gerwig E25544 entity
Predicate notableWork P4 FINISHED
Object Greenberg
Greenberg is a 2010 indie dramedy film directed by Noah Baumbach and starring Ben Stiller as a troubled man reevaluating his life while housesitting in Los Angeles.
E126889 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: Greenberg | Statement: [Greta Gerwig, notableWork, Greenberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Greenberg
Context triple: [Greta Gerwig, notableWork, Greenberg]
  • A. Goodwin
    Goodwin is a masculine given name most notably borne by Goodwin Knight, who served as the 31st governor of California in the mid-20th century.
  • B. Weingarten
    Weingarten is a small locality within the town of Lichtenfels in the Upper Franconia region of Bavaria, Germany.
  • C. Bronstein
    Bronstein is the original family surname of the Russian revolutionary leader Leon Trotsky.
  • D. Gavvy Cravath
    Gavvy Cravath was a power-hitting early 20th-century Major League Baseball outfielder best known for leading the National League in home runs multiple times with the Philadelphia Phillies.
  • E. Charles Goldfarb
    Charles Goldfarb is a computer scientist best known as the principal inventor of SGML, the Standard Generalized Markup Language that laid the foundation for HTML and XML.
  • 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: Greenberg
Triple: [Greta Gerwig, notableWork, Greenberg]
Generated description
Greenberg is a 2010 indie dramedy film directed by Noah Baumbach and starring Ben Stiller as a troubled man reevaluating his life while housesitting in Los Angeles.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Greenberg
Target entity description: Greenberg is a 2010 indie dramedy film directed by Noah Baumbach and starring Ben Stiller as a troubled man reevaluating his life while housesitting in Los Angeles.
  • A. Goodwin
    Goodwin is a masculine given name most notably borne by Goodwin Knight, who served as the 31st governor of California in the mid-20th century.
  • B. Weingarten
    Weingarten is a small locality within the town of Lichtenfels in the Upper Franconia region of Bavaria, Germany.
  • C. Bronstein
    Bronstein is the original family surname of the Russian revolutionary leader Leon Trotsky.
  • D. Gavvy Cravath
    Gavvy Cravath was a power-hitting early 20th-century Major League Baseball outfielder best known for leading the National League in home runs multiple times with the Philadelphia Phillies.
  • E. Charles Goldfarb
    Charles Goldfarb is a computer scientist best known as the principal inventor of SGML, the Standard Generalized Markup Language that laid the foundation for HTML and XML.
  • 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_69a49428d4448190b3b36991ceae87ce completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b9e6134481909f348986a25f65c6 completed March 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac4c4f65888190b48c2d220e62a26b completed March 7, 2026, 4:03 p.m.
NEDg Description generation batch_69ac500036f48190bab0bf4e07d5c9ae completed March 7, 2026, 4:19 p.m.
NED2 Entity disambiguation (via description) batch_69ac508ca8e48190bfea6ad9b6920e78 completed March 7, 2026, 4:21 p.m.
Created at: March 1, 2026, 7:43 p.m.