Triple

T2042481
Position Surface form Disambiguated ID Type / Status
Subject Eastern Iranian languages E44775 entity
Predicate hasMember P10 FINISHED
Object Ishkashimi
Ishkashimi is a lesser-known Eastern Iranian language spoken by small communities in parts of Afghanistan and Tajikistan.
E372341 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: Ishkashimi | Statement: [Eastern Iranian languages, hasMember, Ishkashimi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ishkashimi
Context triple: [Eastern Iranian languages, hasMember, Ishkashimi]
  • A. Kamiyama
    Kamiyama is a Japanese surname borne by various individuals, including artists, athletes, and public figures.
  • B. Tatsuno
    Tatsuno is a city in western Japan known for its traditional soy sauce production and historic townscape within Hyogo Prefecture.
  • C. Akishino
    Akishino is the imperial family name of a branch of Japan’s monarchy, borne by members such as Prince Hisahito and his parents, Crown Prince Fumihito and Crown Princess Kiko.
  • D. Kubashima
    Kubashima is one of the small, uninhabited islets that make up the disputed Senkaku Islands in the East China Sea.
  • E. Ikoma
    Ikoma is a city in Japan known for its scenic setting on the slopes of Mount Ikoma and its role as a residential and commuter hub near Osaka and Nara.
  • 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: Ishkashimi
Triple: [Eastern Iranian languages, hasMember, Ishkashimi]
Generated description
Ishkashimi is a lesser-known Eastern Iranian language spoken by small communities in parts of Afghanistan and Tajikistan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ishkashimi
Target entity description: Ishkashimi is a lesser-known Eastern Iranian language spoken by small communities in parts of Afghanistan and Tajikistan.
  • A. Kamiyama
    Kamiyama is a Japanese surname borne by various individuals, including artists, athletes, and public figures.
  • B. Tatsuno
    Tatsuno is a city in western Japan known for its traditional soy sauce production and historic townscape within Hyogo Prefecture.
  • C. Akishino
    Akishino is the imperial family name of a branch of Japan’s monarchy, borne by members such as Prince Hisahito and his parents, Crown Prince Fumihito and Crown Princess Kiko.
  • D. Kubashima
    Kubashima is one of the small, uninhabited islets that make up the disputed Senkaku Islands in the East China Sea.
  • E. Ikoma
    Ikoma is a city in Japan known for its scenic setting on the slopes of Mount Ikoma and its role as a residential and commuter hub near Osaka and Nara.
  • 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_69a889159ec481908f9e4472d9f480c7 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb95587348190bb5719faeaf0aa5d completed March 7, 2026, 5:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69b4029cfa148190baad6968cf6dad3a completed March 13, 2026, 12:27 p.m.
NEDg Description generation batch_69b40da9e4808190a01d7305d4fdb7f3 completed March 13, 2026, 1:14 p.m.
NED2 Entity disambiguation (via description) batch_69b42d8084c88190a2aae4a883d050a0 completed March 13, 2026, 3:30 p.m.
Created at: March 4, 2026, 7:39 p.m.