Triple

T13854211
Position Surface form Disambiguated ID Type / Status
Subject Resident Evil: The Final Chapter E333020 entity
Predicate starring P1507 FINISHED
Object William Levy
William Levy is a Cuban-American actor and former model known for his roles in telenovelas and films, as well as appearances in mainstream Hollywood productions.
 E1072646 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: William Levy | Statement: [Resident Evil: The Final Chapter, starring, William Levy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: William Levy
Context triple: [Resident Evil: The Final Chapter, starring, William Levy]
  • A. Thomas Levy
    Thomas Levy is the fictional graduate student and long-distance runner protagonist of William Goldman’s thriller novel "Marathon Man."
  • B. Louis Levy
    Louis Levy was a prominent British film music director and composer known for his influential work on early 20th-century cinema scores.
  • C. Michael Levy
    Michael Levy is a film producer known for his work on the action-crime drama movie "Waist Deep."
  • D. Matthew Levy
    Matthew Levy is an actor known for his role in the television sitcom "Sons of Tucson."
  • E. Sam Levy
    Sam Levy is an American cinematographer best known for his frequent collaborations with director Noah Baumbach and his work on acclaimed independent films.
  • 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: William Levy
Triple: [Resident Evil: The Final Chapter, starring, William Levy]
Generated description
William Levy is a Cuban-American actor and former model known for his roles in telenovelas and films, as well as appearances in mainstream Hollywood productions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: William Levy
Target entity description: William Levy is a Cuban-American actor and former model known for his roles in telenovelas and films, as well as appearances in mainstream Hollywood productions.
  • A. Thomas Levy
    Thomas Levy is the fictional graduate student and long-distance runner protagonist of William Goldman’s thriller novel "Marathon Man."
  • B. Louis Levy
    Louis Levy was a prominent British film music director and composer known for his influential work on early 20th-century cinema scores.
  • C. Michael Levy
    Michael Levy is a film producer known for his work on the action-crime drama movie "Waist Deep."
  • D. Matthew Levy
    Matthew Levy is an actor known for his role in the television sitcom "Sons of Tucson."
  • E. Sam Levy
    Sam Levy is an American cinematographer best known for his frequent collaborations with director Noah Baumbach and his work on acclaimed independent films.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02db9c9c81909bb2d2fbfb7394b1 completed April 14, 2026, 9:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69fba1bbee14819082e1a381a5950e07 completed May 6, 2026, 8:17 p.m.
NEDg Description generation batch_69fba5bff3b88190b5fcf3834e419b72 completed May 6, 2026, 8:34 p.m.
NED2 Entity disambiguation (via description) batch_69fba9af1e0c81908d4013410e76535a completed May 6, 2026, 8:50 p.m.
Created at: April 9, 2026, 10:14 p.m.