Triple

T13032005
Position Surface form Disambiguated ID Type / Status
Subject Sayonara E326463 entity
Predicate starring P1507 FINISHED
Object Miiko Taka
Miiko Taka was a Japanese-American actress best known for her breakthrough role opposite Marlon Brando in the 1957 film "Sayonara."
E1017100 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: Miiko Taka | Statement: [Sayonara, starring, Miiko Taka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Miiko Taka
Context triple: [Sayonara, starring, Miiko Taka]
  • A. Takahito
    Takahito, better known by his title Prince Mikasa, was a member of the Japanese imperial family and the youngest son of Emperor Taishō.
  • B. Miki
    Miki is a city in Japan located within Hyogo Prefecture, known for its traditional hardware industry and historical sites.
  • C. Miki
    Miki is a city located in Japan’s Kagawa Prefecture on the island of Shikoku.
  • D. Mogis
    Mogis is the surname of Mike Mogis, an American musician and record producer best known for his work with the indie rock band Bright Eyes and the Saddle Creek Records scene.
  • E. Kintomo Mushakoji
    Kintomo Mushakoji was a Japanese diplomat who served as a key representative of Japan’s government in the 1930s, notably involved in its alignment with Axis powers.
  • 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: Miiko Taka
Triple: [Sayonara, starring, Miiko Taka]
Generated description
Miiko Taka was a Japanese-American actress best known for her breakthrough role opposite Marlon Brando in the 1957 film "Sayonara."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Miiko Taka
Target entity description: Miiko Taka was a Japanese-American actress best known for her breakthrough role opposite Marlon Brando in the 1957 film "Sayonara."
  • A. Takahito
    Takahito, better known by his title Prince Mikasa, was a member of the Japanese imperial family and the youngest son of Emperor Taishō.
  • B. Miki
    Miki is a city in Japan located within Hyogo Prefecture, known for its traditional hardware industry and historical sites.
  • C. Miki
    Miki is a city located in Japan’s Kagawa Prefecture on the island of Shikoku.
  • D. Mogis
    Mogis is the surname of Mike Mogis, an American musician and record producer best known for his work with the indie rock band Bright Eyes and the Saddle Creek Records scene.
  • E. Kintomo Mushakoji
    Kintomo Mushakoji was a Japanese diplomat who served as a key representative of Japan’s government in the 1930s, notably involved in its alignment with Axis powers.
  • 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_69d8076cc45c81908123123f43e69266 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97efe72348190b52fb4068f5fb829 completed April 10, 2026, 10:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbcd25108190a6c4a129cde81534 completed May 3, 2026, 4:15 a.m.
NEDg Description generation batch_69f6cd0d21e08190855dcbee000fc25d completed May 3, 2026, 4:20 a.m.
NED2 Entity disambiguation (via description) batch_69f6ce6b220c8190b1f49a9b2bfce692 completed May 3, 2026, 4:26 a.m.
Created at: April 9, 2026, 8:54 p.m.