Triple

T20566628
Position Surface form Disambiguated ID Type / Status
Subject Kong Ji E504980 entity
Predicate honorificTitle P2097 FINISHED
Object Zisi Zi
Zisi Zi is the honorific name of Kong Ji, a prominent Confucian philosopher and grandson of Confucius.
 E1438286 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: Zisi Zi | Statement: [Kong Ji, honorificTitle, Zisi Zi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zisi Zi
Context triple: [Kong Ji, honorificTitle, Zisi Zi]
  • A. Qingzi
    Qingzi is the courtesy name of Xunzi, an influential Confucian philosopher of the Warring States period known for his emphasis on ritual, education, and the inherently selfish nature of humans.
  • B. Zhizhi
    Zhizhi was the era name used during the brief reign of Gegeen Khan, a Yuan dynasty emperor of the early 14th century.
  • C. Chuanzhi
    Chuanzhi is the given name of Liu Chuanzhi, the Chinese entrepreneur best known as the founder of Lenovo.
  • D. Zǐjìnchéng
    Zǐjìnchéng is the Mandarin Chinese name (in pinyin) for the Forbidden City, the historic imperial palace complex in Beijing.
  • E. Xiaoyanzi
    Xiaoyanzi is a lively, mischievous young woman and one of the main protagonists in the popular Chinese television drama "My Fair Princess" (Huan Zhu Ge Ge).
  • 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: Zisi Zi
Triple: [Kong Ji, honorificTitle, Zisi Zi]
Generated description
Zisi Zi is the honorific name of Kong Ji, a prominent Confucian philosopher and grandson of Confucius.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zisi Zi
Target entity description: Zisi Zi is the honorific name of Kong Ji, a prominent Confucian philosopher and grandson of Confucius.
  • A. Qingzi
    Qingzi is the courtesy name of Xunzi, an influential Confucian philosopher of the Warring States period known for his emphasis on ritual, education, and the inherently selfish nature of humans.
  • B. Zhizhi
    Zhizhi was the era name used during the brief reign of Gegeen Khan, a Yuan dynasty emperor of the early 14th century.
  • C. Chuanzhi
    Chuanzhi is the given name of Liu Chuanzhi, the Chinese entrepreneur best known as the founder of Lenovo.
  • D. Zǐjìnchéng
    Zǐjìnchéng is the Mandarin Chinese name (in pinyin) for the Forbidden City, the historic imperial palace complex in Beijing.
  • E. Xiaoyanzi
    Xiaoyanzi is a lively, mischievous young woman and one of the main protagonists in the popular Chinese television drama "My Fair Princess" (Huan Zhu Ge Ge).
  • 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_69e0b4b6587c8190aee63dc7cff244ea completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a7a33f7c8190966da03528dfe8aa completed April 20, 2026, 10:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08acdffa2c8190a87c367eb068e2cf completed May 16, 2026, 5:44 p.m.
NEDg Description generation batch_6a08ad96b2a081908d32e335c5265eec completed May 16, 2026, 5:47 p.m.
NED2 Entity disambiguation (via description) batch_6a08ae19eca08190ada48b48105be62d completed May 16, 2026, 5:49 p.m.
Created at: April 16, 2026, 11:39 a.m.