Triple

T120115
Position Surface form Disambiguated ID Type / Status
Subject The Mark of Zorro E2426 entity
Predicate screenwriter P2831 FINISHED
Object Eugene Miller
Eugene Miller was a screenwriter best known for his work on classic Hollywood films such as "The Mark of Zorro."
 E75922 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: Eugene Miller | Statement: [The Mark of Zorro, screenwriter, Eugene Miller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Eugene Miller
Context triple: [The Mark of Zorro, screenwriter, Eugene Miller]
  • A. George Boemler
    George Boemler was a film editor known for his work on classic Hollywood productions, including the musical comedy "High Society."
  • B. Johnston McCulley
    Johnston McCulley was an American writer best known as the creator of the swashbuckling masked hero Zorro.
  • C. Don Brochu
    Don Brochu is a film editor best known for his work on major Hollywood movies, including the hit thriller "The Bodyguard."
  • D. Emile Sherman
    Emile Sherman is an Australian film and television producer best known for co-producing the Academy Award–winning film "The King’s Speech" and co-founding the production company See-Saw Films.
  • E. Oscar Neebe
    Oscar Neebe was an American labor activist and anarchist who was controversially convicted in connection with the 1886 Haymarket affair in Chicago.
  • 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: Eugene Miller
Triple: [The Mark of Zorro, screenwriter, Eugene Miller]
Generated description
Eugene Miller was a screenwriter best known for his work on classic Hollywood films such as "The Mark of Zorro."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Eugene Miller
Target entity description: Eugene Miller was a screenwriter best known for his work on classic Hollywood films such as "The Mark of Zorro."
  • A. George Boemler
    George Boemler was a film editor known for his work on classic Hollywood productions, including the musical comedy "High Society."
  • B. Johnston McCulley
    Johnston McCulley was an American writer best known as the creator of the swashbuckling masked hero Zorro.
  • C. Don Brochu
    Don Brochu is a film editor best known for his work on major Hollywood movies, including the hit thriller "The Bodyguard."
  • D. Emile Sherman
    Emile Sherman is an Australian film and television producer best known for co-producing the Academy Award–winning film "The King’s Speech" and co-founding the production company See-Saw Films.
  • E. Oscar Neebe
    Oscar Neebe was an American labor activist and anarchist who was controversially convicted in connection with the 1886 Haymarket affair in Chicago.
  • 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_69a2506c5428819085c28a8884790e29 completed Feb. 28, 2026, 2:18 a.m.
NER Named-entity recognition batch_69a25715cfb881909ffb488f21a4a16d completed Feb. 28, 2026, 2:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69a5291da6c081908ebe0b83a8f3cfa0 completed March 2, 2026, 6:07 a.m.
NEDg Description generation batch_69a52a74bdc08190a4b5cf466d11d6b5 completed March 2, 2026, 6:13 a.m.
NED2 Entity disambiguation (via description) batch_69a52acd26948190b1110721f1a38d05 completed March 2, 2026, 6:14 a.m.
Created at: Feb. 28, 2026, 2:24 a.m.