Triple

T12608309
Position Surface form Disambiguated ID Type / Status
Subject Princess Arisugawa Yoriko E301041 entity
Predicate familyName P18 FINISHED
Object Arisugawa
Arisugawa is a Japanese family name historically associated with aristocratic and imperial lineages.
E1182457 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: Arisugawa | Statement: [Princess Arisugawa Yoriko, familyName, Arisugawa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arisugawa
Context triple: [Princess Arisugawa Yoriko, familyName, Arisugawa]
  • A. Yamatogawa
    Yamatogawa is the romanized name of the Yamato River, a significant waterway in the Kansai region of Japan.
  • B. Takinogawa
    Takinogawa is a residential district in Kita Ward, Tokyo, known for its quiet neighborhoods and convenient urban access.
  • C. Shinano River
    The Shinano River is Japan’s longest river, flowing through central Honshu before emptying into the Sea of Japan.
  • D. Futakotamagawa
    Futakotamagawa is a riverside commercial and residential district in Tokyo known for its large shopping complexes, upscale housing, and scenic Tama River views.
  • E. Sukagawa
    Sukagawa is a city in central Fukushima Prefecture, Japan, known for its historic role as a post town and its annual Taimatsu Akashi fire festival.
  • 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: Arisugawa
Triple: [Princess Arisugawa Yoriko, familyName, Arisugawa]
Generated description
Arisugawa is a Japanese family name historically associated with aristocratic and imperial lineages.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Arisugawa
Target entity description: Arisugawa is a Japanese family name historically associated with aristocratic and imperial lineages.
  • A. Yamatogawa
    Yamatogawa is the romanized name of the Yamato River, a significant waterway in the Kansai region of Japan.
  • B. Takinogawa
    Takinogawa is a residential district in Kita Ward, Tokyo, known for its quiet neighborhoods and convenient urban access.
  • C. Shinano River
    The Shinano River is Japan’s longest river, flowing through central Honshu before emptying into the Sea of Japan.
  • D. Futakotamagawa
    Futakotamagawa is a riverside commercial and residential district in Tokyo known for its large shopping complexes, upscale housing, and scenic Tama River views.
  • E. Sukagawa
    Sukagawa is a city in central Fukushima Prefecture, Japan, known for its historic role as a post town and its annual Taimatsu Akashi fire festival.
  • 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_69d7bdea2ca881908f379526c13b1145 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d954e90efc81909951dbe698afa851 completed April 10, 2026, 7:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb02b55f4819098f2b18fcf17ef0e completed May 9, 2026, 10:07 p.m.
NEDg Description generation batch_69ffb0ae72e48190a3c799a7f242c94c completed May 9, 2026, 10:09 p.m.
NED2 Entity disambiguation (via description) batch_69ffb0e11fc481908a2609979dea4d59 completed May 9, 2026, 10:10 p.m.
Created at: April 9, 2026, 5:11 p.m.