Triple

T1913078
Position Surface form Disambiguated ID Type / Status
Subject Miskolc E38152 entity
Predicate twinnedWith P1072 FINISHED
Object Asan
Asan is a city in South Korea known for its hot springs, historical sites, and growing role as an industrial and educational center.
E215809 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: Asan | Statement: [Miskolc, twinnedWith, Asan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Asan
Context triple: [Miskolc, twinnedWith, Asan]
  • A. Akhasheni
    Akhasheni is a Georgian red wine appellation from the Kakheti region, known for its naturally semi-sweet wines made primarily from Saperavi grapes.
  • B. Sana'i
    Sana'i was a pioneering 12th-century Persian Sufi poet whose mystical and didactic works profoundly shaped later poets, including Rumi.
  • C. Askim
    Askim is a town in southeastern Norway that serves as one of the locations for Østfold University College’s campuses.
  • D. Atsi
    Atsi is a regional dialect of the Fang language spoken by Fang communities in Central Africa.
  • E. Asago
    Asago is a city in northern Hyōgo Prefecture, Japan, known for its mountainous scenery, historic castle ruins, and hot spring resorts.
  • 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: Asan
Triple: [Miskolc, twinnedWith, Asan]
Generated description
Asan is a city in South Korea known for its hot springs, historical sites, and growing role as an industrial and educational center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Asan
Target entity description: Asan is a city in South Korea known for its hot springs, historical sites, and growing role as an industrial and educational center.
  • A. Akhasheni
    Akhasheni is a Georgian red wine appellation from the Kakheti region, known for its naturally semi-sweet wines made primarily from Saperavi grapes.
  • B. Sana'i
    Sana'i was a pioneering 12th-century Persian Sufi poet whose mystical and didactic works profoundly shaped later poets, including Rumi.
  • C. Askim
    Askim is a town in southeastern Norway that serves as one of the locations for Østfold University College’s campuses.
  • D. Atsi
    Atsi is a regional dialect of the Fang language spoken by Fang communities in Central Africa.
  • E. Asago
    Asago is a city in northern Hyōgo Prefecture, Japan, known for its mountainous scenery, historic castle ruins, and hot spring resorts.
  • 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_69a8862a26088190aae5243695aeefc0 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb1e26b948190aa194c30755ac5df completed March 7, 2026, 5:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69adf3d5972881908856b75b324a1ad2 completed March 8, 2026, 10:10 p.m.
NEDg Description generation batch_69adf44290748190b882559de536af09 completed March 8, 2026, 10:12 p.m.
NED2 Entity disambiguation (via description) batch_69adf4d0ac58819096659706ef0785d0 completed March 8, 2026, 10:14 p.m.
Created at: March 4, 2026, 7:35 p.m.