Triple

T5160604
Position Surface form Disambiguated ID Type / Status
Subject 2 Fast 2 Furious E116425 entity
Predicate starring P1507 FINISHED
Object Devon Aoki
Devon Aoki is an American model and actress best known for her roles in action films like "2 Fast 2 Furious" and "Sin City."
E499463 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: Devon Aoki | Statement: [2 Fast 2 Furious, starring, Devon Aoki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Devon Aoki
Context triple: [2 Fast 2 Furious, starring, Devon Aoki]
  • A. Kelly Matsumoto
    Kelly Matsumoto is a film editor known for her work on major Hollywood productions, including the science fiction blockbuster "Star Trek Beyond."
  • B. Jordan Nagai
    Jordan Nagai is an American former child voice actor best known for voicing the character Russell in Pixar's animated film "Up."
  • C. Kerri Higuchi
    Kerri Higuchi is a Korean American actress and director known for her work in film and television and for being married to actor John Cho.
  • D. Daryn Okada
    Daryn Okada is an American cinematographer known for his work on a wide range of studio films, including popular comedies and genre movies.
  • E. Rinako Kikuchi
    Rinako Kikuchi is the stage name of Japanese actress Yuriko Kikuchi, known for her acclaimed performances in both Japanese cinema and international 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: Devon Aoki
Triple: [2 Fast 2 Furious, starring, Devon Aoki]
Generated description
Devon Aoki is an American model and actress best known for her roles in action films like "2 Fast 2 Furious" and "Sin City."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Devon Aoki
Target entity description: Devon Aoki is an American model and actress best known for her roles in action films like "2 Fast 2 Furious" and "Sin City."
  • A. Kelly Matsumoto
    Kelly Matsumoto is a film editor known for her work on major Hollywood productions, including the science fiction blockbuster "Star Trek Beyond."
  • B. Jordan Nagai
    Jordan Nagai is an American former child voice actor best known for voicing the character Russell in Pixar's animated film "Up."
  • C. Kerri Higuchi
    Kerri Higuchi is a Korean American actress and director known for her work in film and television and for being married to actor John Cho.
  • D. Daryn Okada
    Daryn Okada is an American cinematographer known for his work on a wide range of studio films, including popular comedies and genre movies.
  • E. Rinako Kikuchi
    Rinako Kikuchi is the stage name of Japanese actress Yuriko Kikuchi, known for her acclaimed performances in both Japanese cinema and international 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_69bd445edb3881909b93b34d260717fc completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd79073a54819080cd1e8de6fe906a completed March 20, 2026, 4:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69bed92b3ab48190900cf5c246dba433 completed March 21, 2026, 5:45 p.m.
NEDg Description generation batch_69beda3bfee08190a6e1d8b06739cade completed March 21, 2026, 5:49 p.m.
NED2 Entity disambiguation (via description) batch_69beda93175481908c79010c7fe6897e completed March 21, 2026, 5:51 p.m.
Created at: March 20, 2026, 1:44 p.m.