Triple

T4041631
Position Surface form Disambiguated ID Type / Status
Subject Gion district E83963 entity
Predicate famousFor P22 FINISHED
Object geiko
A geiko is a highly trained traditional Japanese female entertainer from Kyoto, skilled in classical arts such as dance, music, and refined social performance.
 E409352 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: geiko | Statement: [Gion district, famousFor, geiko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: geiko
Context triple: [Gion district, famousFor, geiko]
  • A. gohei
    Gohei are traditional Shinto ritual wands, typically made of a wooden stick adorned with zigzagging paper streamers, used in purification and offerings to kami.
  • B. GEKUT
    GEKUT is the UN/LOCODE identifier for the city of Kutaisi in Georgia, used in international trade and transport logistics.
  • C. Gein
    Gein is a metro station in Amsterdam, Netherlands, serving as one of the termini of the city's metro network.
  • D. Geita
    Geita is a town in northwestern Tanzania that serves as an administrative and commercial center for the surrounding gold-mining region.
  • E. Kyojin
    Kyojin is the popular nickname of the Yomiuri Giants, one of Japan’s most historic and successful professional baseball teams.
  • 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: geiko
Triple: [Gion district, famousFor, geiko]
Generated description
A geiko is a highly trained traditional Japanese female entertainer from Kyoto, skilled in classical arts such as dance, music, and refined social performance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: geiko
Target entity description: A geiko is a highly trained traditional Japanese female entertainer from Kyoto, skilled in classical arts such as dance, music, and refined social performance.
  • A. gohei
    Gohei are traditional Shinto ritual wands, typically made of a wooden stick adorned with zigzagging paper streamers, used in purification and offerings to kami.
  • B. GEKUT
    GEKUT is the UN/LOCODE identifier for the city of Kutaisi in Georgia, used in international trade and transport logistics.
  • C. Gein
    Gein is a metro station in Amsterdam, Netherlands, serving as one of the termini of the city's metro network.
  • D. Geita
    Geita is a town in northwestern Tanzania that serves as an administrative and commercial center for the surrounding gold-mining region.
  • E. Kyojin
    Kyojin is the popular nickname of the Yomiuri Giants, one of Japan’s most historic and successful professional baseball teams.
  • 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_69aed92f7cf0819098e0539bdcc3767f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefb3a9314819095dcf47675eedb48 completed March 9, 2026, 4:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5564d0fb881909ba645714be27b95 completed March 14, 2026, 12:36 p.m.
NEDg Description generation batch_69b55a291d8c8190976e764011692ba0 completed March 14, 2026, 12:52 p.m.
NED2 Entity disambiguation (via description) batch_69b55a9ec7e88190bc5d165fd666f4b3 completed March 14, 2026, 12:54 p.m.
Created at: March 9, 2026, 3:37 p.m.