Triple

T8625459
Position Surface form Disambiguated ID Type / Status
Subject Mother (1926 film) E204269 entity
Predicate screenwriter P2831 FINISHED
Object Nathan Zarkhi
Nathan Zarkhi was a screenwriter known for his work on early Soviet cinema, including contributing to the script of the 1926 film "Mother."
E747556 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: Nathan Zarkhi | Statement: [Mother (1926 film), screenwriter, Nathan Zarkhi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nathan Zarkhi
Context triple: [Mother (1926 film), screenwriter, Nathan Zarkhi]
  • A. Adam Zertal
    Adam Zertal was an Israeli archaeologist best known for his extensive excavations and research in the biblical heartland of Samaria, including the controversial site on Mount Ebal.
  • B. Nathan Cohen
    Nathan Cohen is the paternal grandfather of Lorca Cohen, the daughter of renowned Canadian singer-songwriter Leonard Cohen.
  • C. Max Zaritsky
    Max Zaritsky was an American labor leader and union organizer who played a key role in the early development of industrial unionism in the United States.
  • D. Nathan Waks
    Nathan Waks is an Australian cellist, composer, and music producer known for his work on film scores and classical music projects.
  • E. Jonathan Benassaya
    Jonathan Benassaya is a French entrepreneur best known for co-founding the music streaming service Deezer.
  • 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: Nathan Zarkhi
Triple: [Mother (1926 film), screenwriter, Nathan Zarkhi]
Generated description
Nathan Zarkhi was a screenwriter known for his work on early Soviet cinema, including contributing to the script of the 1926 film "Mother."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nathan Zarkhi
Target entity description: Nathan Zarkhi was a screenwriter known for his work on early Soviet cinema, including contributing to the script of the 1926 film "Mother."
  • A. Adam Zertal
    Adam Zertal was an Israeli archaeologist best known for his extensive excavations and research in the biblical heartland of Samaria, including the controversial site on Mount Ebal.
  • B. Nathan Cohen
    Nathan Cohen is the paternal grandfather of Lorca Cohen, the daughter of renowned Canadian singer-songwriter Leonard Cohen.
  • C. Max Zaritsky
    Max Zaritsky was an American labor leader and union organizer who played a key role in the early development of industrial unionism in the United States.
  • D. Nathan Waks
    Nathan Waks is an Australian cellist, composer, and music producer known for his work on film scores and classical music projects.
  • E. Jonathan Benassaya
    Jonathan Benassaya is a French entrepreneur best known for co-founding the music streaming service Deezer.
  • 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_69ca834a4ea0819094970dceb9e389f3 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc472a07908190a2368975459543f9 completed March 31, 2026, 10:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebbf03c688190a989f16675f6e8a6 completed April 2, 2026, 6:56 p.m.
NEDg Description generation batch_69cebdd3ae908190bc4108b766585cbc completed April 2, 2026, 7:04 p.m.
NED2 Entity disambiguation (via description) batch_69cebf1825008190a97cd2df10f8e406 completed April 2, 2026, 7:10 p.m.
Created at: March 30, 2026, 6:26 p.m.