Triple

T16761071
Position Surface form Disambiguated ID Type / Status
Subject The Big Cube E407343 entity
Predicate hasCharacter P2308 FINISHED
Object Adriana Roman
Adriana Roman is a fictional character from the 1969 psychological thriller film "The Big Cube."
E1237600 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: Adriana Roman | Statement: [The Big Cube, hasCharacter, Adriana Roman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adriana Roman
Context triple: [The Big Cube, hasCharacter, Adriana Roman]
  • A. Adriana Ozores
    Adriana Ozores is a Spanish actress known for her extensive work in film, television, and theater, and as a member of the prominent Ozores acting family.
  • B. Adriana Medina
    Adriana Medina is a contemporary perfumer known for creating modern, luminous fragrances for major luxury brands such as Lancôme.
  • C. Letícia Román
    Letícia Román is an Italian actress best known for her roles in 1960s films, including opposite Elvis Presley in the musical comedy "G.I. Blues."
  • D. María Romo
    María Romo is a Spanish actress known for her work in film and television.
  • E. Mariola Fuentes
    Mariola Fuentes is a Spanish actress known for her character roles in films and television, particularly in the works of director Pedro Almodóvar.
  • 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: Adriana Roman
Triple: [The Big Cube, hasCharacter, Adriana Roman]
Generated description
Adriana Roman is a fictional character from the 1969 psychological thriller film "The Big Cube."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Adriana Roman
Target entity description: Adriana Roman is a fictional character from the 1969 psychological thriller film "The Big Cube."
  • A. Adriana Ozores
    Adriana Ozores is a Spanish actress known for her extensive work in film, television, and theater, and as a member of the prominent Ozores acting family.
  • B. Adriana Medina
    Adriana Medina is a contemporary perfumer known for creating modern, luminous fragrances for major luxury brands such as Lancôme.
  • C. Letícia Román
    Letícia Román is an Italian actress best known for her roles in 1960s films, including opposite Elvis Presley in the musical comedy "G.I. Blues."
  • D. María Romo
    María Romo is a Spanish actress known for her work in film and television.
  • E. Mariola Fuentes
    Mariola Fuentes is a Spanish actress known for her character roles in films and television, particularly in the works of director Pedro Almodóvar.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3abec638c81909d71ff452a4123c9 completed April 18, 2026, 4:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c2993f4c8190aecf29a4bcbf7b6a completed May 10, 2026, 5:38 p.m.
NEDg Description generation batch_6a00c41e33c481908694a0e62f630b29 completed May 10, 2026, 5:45 p.m.
NED2 Entity disambiguation (via description) batch_6a00c4771f2481909189bd5c2646caf2 completed May 10, 2026, 5:46 p.m.
Created at: April 10, 2026, 5:21 a.m.