Triple

T20331800
Position Surface form Disambiguated ID Type / Status
Subject Maki Horikita E492500 entity
Predicate familyName P18 FINISHED
Object Horikita
Horikita is a Japanese surname most notably associated with actress Maki Horikita, known for her roles in popular television dramas and films.
 E1486932 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: Horikita | Statement: [Maki Horikita, familyName, Horikita]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Horikita
Context triple: [Maki Horikita, familyName, Horikita]
  • A. Haishima
    Haishima is a Japanese surname most notably borne by composer Kuniaki Haishima, known for his work on film, television, and video game soundtracks.
  • B. Hironori
    Hironori is a larger composite entity or system of which Hiro is a constituent part.
  • C. Sadaharu
    Sadaharu is the given name of Sadaharu Oh, the legendary Japanese-Taiwanese baseball player and home run record holder.
  • D. Furutaka
    Furutaka was a Japanese heavy cruiser of the Imperial Japanese Navy that served during the interwar period and World War II.
  • E. Itagaki
    Itagaki is a Japanese surname associated with several notable historical and contemporary figures in Japan.
  • 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: Horikita
Triple: [Maki Horikita, familyName, Horikita]
Generated description
Horikita is a Japanese surname most notably associated with actress Maki Horikita, known for her roles in popular television dramas and films.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Horikita
Target entity description: Horikita is a Japanese surname most notably associated with actress Maki Horikita, known for her roles in popular television dramas and films.
  • A. Haishima
    Haishima is a Japanese surname most notably borne by composer Kuniaki Haishima, known for his work on film, television, and video game soundtracks.
  • B. Hironori
    Hironori is a larger composite entity or system of which Hiro is a constituent part.
  • C. Sadaharu
    Sadaharu is the given name of Sadaharu Oh, the legendary Japanese-Taiwanese baseball player and home run record holder.
  • D. Furutaka
    Furutaka was a Japanese heavy cruiser of the Imperial Japanese Navy that served during the interwar period and World War II.
  • E. Itagaki
    Itagaki is a Japanese surname associated with several notable historical and contemporary figures in Japan.
  • 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_69e0b4a1a09881908d97270d6971a25a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e677e7baf481909282293d78597634 completed April 20, 2026, 7 p.m.
NED1 Entity disambiguation (via context triple) batch_6a09cfd76e4081908de738aa0184c8d3 completed May 17, 2026, 2:25 p.m.
NEDg Description generation batch_6a09d3c93fc08190a58e1e039ca1b419 completed May 17, 2026, 2:42 p.m.
NED2 Entity disambiguation (via description) batch_6a09d42e65d881908d4d2731a9de0cf5 completed May 17, 2026, 2:43 p.m.
Created at: April 16, 2026, 11:22 a.m.