Triple

T13174286
Position Surface form Disambiguated ID Type / Status
Subject Koyama Mihoko E313059 entity
Predicate familyName P18 FINISHED
Object Koyama
Koyama is a Japanese surname borne by various notable individuals across fields such as entertainment, sports, and the arts.
 E1269517 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: Koyama | Statement: [Koyama Mihoko, familyName, Koyama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Koyama
Context triple: [Koyama Mihoko, familyName, Koyama]
  • A. Kamiyama
    Kamiyama is a Japanese surname borne by various individuals, including artists, athletes, and public figures.
  • B. Yoiyama
    Yoiyama is the lively evening street festival held before the main Gion Matsuri parade in Kyoto, featuring illuminated festival floats, food stalls, and traditional music.
  • C. Nagayama
    Nagayama is a residential and commercial district within Tama New Town in Tokyo, Japan, known for its planned urban layout and local amenities.
  • D. Kominato
    Kominato is a coastal area in present-day Chiba Prefecture, Japan, historically known as the birthplace of the Buddhist monk Nichiren.
  • E. Urakawa
    Urakawa is a coastal town in Hokkaido, Japan, known for its horse breeding industry and scenic Pacific shoreline.
  • 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: Koyama
Triple: [Koyama Mihoko, familyName, Koyama]
Generated description
Koyama is a Japanese surname borne by various notable individuals across fields such as entertainment, sports, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Koyama
Target entity description: Koyama is a Japanese surname borne by various notable individuals across fields such as entertainment, sports, and the arts.
  • A. Kamiyama
    Kamiyama is a Japanese surname borne by various individuals, including artists, athletes, and public figures.
  • B. Yoiyama
    Yoiyama is the lively evening street festival held before the main Gion Matsuri parade in Kyoto, featuring illuminated festival floats, food stalls, and traditional music.
  • C. Nagayama
    Nagayama is a residential and commercial district within Tama New Town in Tokyo, Japan, known for its planned urban layout and local amenities.
  • D. Kominato
    Kominato is a coastal area in present-day Chiba Prefecture, Japan, historically known as the birthplace of the Buddhist monk Nichiren.
  • E. Urakawa
    Urakawa is a coastal town in Hokkaido, Japan, known for its horse breeding industry and scenic Pacific shoreline.
  • 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_69d806ac3ee081909b2fd27d060aa974 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98c303e3c819086cf0f0b6d9e61ca completed April 10, 2026, 11:48 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01afd6121081908345fe7dd941c780 completed May 11, 2026, 10:30 a.m.
NEDg Description generation batch_6a01b259ba9c8190878946190ff21e7d completed May 11, 2026, 10:41 a.m.
NED2 Entity disambiguation (via description) batch_6a01b2cf4e608190ae1d40ee5b7cc427 completed May 11, 2026, 10:43 a.m.
Created at: April 9, 2026, 9:14 p.m.