Triple

T1099155
Position Surface form Disambiguated ID Type / Status
Subject William C. deMille E24338 entity
Predicate spouse P13 FINISHED
Object Clara Beranger
Clara Beranger was an American screenwriter of the silent film era, known for her work with Paramount Pictures and her contributions to early Hollywood cinema.
E156028 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: Clara Beranger | Statement: [William C. deMille, spouse, Clara Beranger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Clara Beranger
Context triple: [William C. deMille, spouse, Clara Beranger]
  • A. Claudine Denosse
    Claudine Denosse was the wife of the prominent 16th-century Reformed theologian and Calvinist leader Theodore Beza.
  • B. Marguerite Gaudelet
    Marguerite Gaudelet was the wife of French civil engineer Gustave Eiffel, famed designer of the Eiffel Tower.
  • C. Julie Clary
    Julie Clary was a French noblewoman who became Queen consort of Naples and later of Spain through her marriage into the Bonaparte family.
  • D. Camille Lefèvre
    Camille Lefèvre was a Swiss architect best known for co-designing the Palais des Nations, the former League of Nations headquarters in Geneva.
  • E. Estelle
    Estelle is a British singer, rapper, and songwriter best known for her hit single "American Boy" featuring Kanye West.
  • 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: Clara Beranger
Triple: [William C. deMille, spouse, Clara Beranger]
Generated description
Clara Beranger was an American screenwriter of the silent film era, known for her work with Paramount Pictures and her contributions to early Hollywood cinema.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Clara Beranger
Target entity description: Clara Beranger was an American screenwriter of the silent film era, known for her work with Paramount Pictures and her contributions to early Hollywood cinema.
  • A. Claudine Denosse
    Claudine Denosse was the wife of the prominent 16th-century Reformed theologian and Calvinist leader Theodore Beza.
  • B. Marguerite Gaudelet
    Marguerite Gaudelet was the wife of French civil engineer Gustave Eiffel, famed designer of the Eiffel Tower.
  • C. Julie Clary
    Julie Clary was a French noblewoman who became Queen consort of Naples and later of Spain through her marriage into the Bonaparte family.
  • D. Camille Lefèvre
    Camille Lefèvre was a Swiss architect best known for co-designing the Palais des Nations, the former League of Nations headquarters in Geneva.
  • E. Estelle
    Estelle is a British singer, rapper, and songwriter best known for her hit single "American Boy" featuring Kanye West.
  • 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_69a4940542308190ac2a0b1f730b7cfc completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b9bd4eec819094fe09e13b7b07b8 completed March 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69acce55b5748190b54b8205a735ae89 completed March 8, 2026, 1:18 a.m.
NEDg Description generation batch_69accf47541481909f2032cdf8e4272b completed March 8, 2026, 1:22 a.m.
NED2 Entity disambiguation (via description) batch_69accff8af488190a7580cf7c02ceed9 completed March 8, 2026, 1:25 a.m.
Created at: March 1, 2026, 7:43 p.m.