Triple

T2073556
Position Surface form Disambiguated ID Type / Status
Subject Mengjiang E44869 entity
Predicate capital P234 FINISHED
Object Kalgan
Kalgan is a historical city in northern China, known today as Zhangjiakou, that served as an important gateway between China and Mongolia and a strategic center in various regional regimes.
 E231386 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: Kalgan | Statement: [Mengjiang, capital, Kalgan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kalgan
Context triple: [Mengjiang, capital, Kalgan]
  • A. Sholto
    Sholto is a masculine given name of Scottish origin, historically associated with figures such as military leaders and nobles.
  • B. Wushe
    Wushe is a mountainous region in central Taiwan historically inhabited by Indigenous Seediq people and known as the site of the 1930 Wushe Incident.
  • C. Benambra
    Benambra is a Victorian state electoral district in Australia that covers a large rural area in the state's northeast, including the city of Wodonga.
  • D. Temeswar
    Temeswar (Timișoara) is a major city in western Romania known for its multicultural heritage and role in the 1989 Romanian Revolution.
  • E. Koutiala
    Koutiala is a major city in southern Mali known as an important center for cotton production and agriculture.
  • 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: Kalgan
Triple: [Mengjiang, capital, Kalgan]
Generated description
Kalgan is a historical city in northern China, known today as Zhangjiakou, that served as an important gateway between China and Mongolia and a strategic center in various regional regimes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kalgan
Target entity description: Kalgan is a historical city in northern China, known today as Zhangjiakou, that served as an important gateway between China and Mongolia and a strategic center in various regional regimes.
  • A. Sholto
    Sholto is a masculine given name of Scottish origin, historically associated with figures such as military leaders and nobles.
  • B. Wushe
    Wushe is a mountainous region in central Taiwan historically inhabited by Indigenous Seediq people and known as the site of the 1930 Wushe Incident.
  • C. Benambra
    Benambra is a Victorian state electoral district in Australia that covers a large rural area in the state's northeast, including the city of Wodonga.
  • D. Temeswar
    Temeswar (Timișoara) is a major city in western Romania known for its multicultural heritage and role in the 1989 Romanian Revolution.
  • E. Koutiala
    Koutiala is a major city in southern Mali known as an important center for cotton production and agriculture.
  • 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_69a88916c2b48190a5ca2e9b12cad3ed completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abba101c008190840763d2f28fa8d7 completed March 7, 2026, 5:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae272ee27c8190a4bb4690961dccf6 completed March 9, 2026, 1:49 a.m.
NEDg Description generation batch_69ae27b2c9d08190b1950abd8d41d3b3 completed March 9, 2026, 1:51 a.m.
NED2 Entity disambiguation (via description) batch_69ae2817ce3c81908e48170760cf98ef completed March 9, 2026, 1:53 a.m.
Created at: March 4, 2026, 7:41 p.m.