Triple

T19578409
Position Surface form Disambiguated ID Type / Status
Subject 신라 E489921 entity
Predicate alternateName P39 FINISHED
Object 서라벌
서라벌은 고대 한반도의 삼국 가운데 하나인 신라의 수도로, 오늘날 경주 일대를 가리키는 옛 지명이다.
 E1383286 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: 서라벌 | Statement: [신라, alternateName, 서라벌]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 서라벌
Context triple: [신라, alternateName, 서라벌]
  • A. The Mara
    The Mara is a renowned wildlife-rich region in southwestern Kenya, best known for the Maasai Mara National Reserve and the annual Great Migration of wildebeest and other animals.
  • B. The Mara
    The Mara is a quick-service restaurant at Disney’s Animal Kingdom Lodge offering African-inspired and American dishes in a casual setting.
  • C. Sabie
    Sabie is a small forestry and tourism town in northeastern South Africa, known as a gateway to waterfalls and scenic routes near the Drakensberg escarpment.
  • D. Savanna-la-Mar
    Savanna-la-Mar is a coastal town in western Jamaica that serves as the capital of Westmoreland Parish and a key commercial center in the region.
  • E. Choba
    Choba is a prominent town in Rivers State, Nigeria, known for hosting the main campus of the University of Port Harcourt and serving as a key residential and commercial hub in the Obio-Akpor area.
  • 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: 서라벌
Triple: [신라, alternateName, 서라벌]
Generated description
서라벌은 고대 한반도의 삼국 가운데 하나인 신라의 수도로, 오늘날 경주 일대를 가리키는 옛 지명이다.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: 서라벌
Target entity description: 서라벌은 고대 한반도의 삼국 가운데 하나인 신라의 수도로, 오늘날 경주 일대를 가리키는 옛 지명이다.
  • A. The Mara
    The Mara is a quick-service restaurant at Disney’s Animal Kingdom Lodge offering African-inspired and American dishes in a casual setting.
  • B. The Mara
    The Mara is a renowned wildlife-rich region in southwestern Kenya, best known for the Maasai Mara National Reserve and the annual Great Migration of wildebeest and other animals.
  • C. Sabie
    Sabie is a small forestry and tourism town in northeastern South Africa, known as a gateway to waterfalls and scenic routes near the Drakensberg escarpment.
  • D. Savanna-la-Mar
    Savanna-la-Mar is a coastal town in western Jamaica that serves as the capital of Westmoreland Parish and a key commercial center in the region.
  • E. Choba
    Choba is a prominent town in Rivers State, Nigeria, known for hosting the main campus of the University of Port Harcourt and serving as a key residential and commercial hub in the Obio-Akpor area.
  • 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_69d8e8dd9374819098e36349b3211663 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6402693d88190a828c0e136895783 completed April 20, 2026, 3:03 p.m.
NED1 Entity disambiguation (via context triple) batch_6a075792581881909443cecc6a9212e4 completed May 15, 2026, 5:27 p.m.
NEDg Description generation batch_6a0758be89108190adb2369750eb90ca completed May 15, 2026, 5:32 p.m.
NED2 Entity disambiguation (via description) batch_6a07599d4c988190a32a0aa9e561a61d completed May 15, 2026, 5:36 p.m.
Created at: April 10, 2026, 1:42 p.m.