Triple

T19047742
Position Surface form Disambiguated ID Type / Status
Subject Book from the Sky E466177 entity
Predicate alsoKnownAs P39 FINISHED
Object Tiānshū
Tiānshū is an experimental Chinese artwork and book project by Xu Bing featuring thousands of invented, unreadable characters that resemble traditional Chinese script.
 E1356454 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: Tiānshū | Statement: [Book from the Sky, alsoKnownAs, Tiānshū]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tiānshū
Context triple: [Book from the Sky, alsoKnownAs, Tiānshū]
  • A. Shengzhi
    Shengzhi is the given name of Tang Shengzhi, a prominent Chinese Nationalist general active during the early 20th century.
  • B. Lishu
    Lishu is an ancient Chinese clerical script that emerged during the Qin and Han dynasties, marking a key transition from earlier seal scripts to more regular, standardized writing forms.
  • C. Yuanpei
    Yuanpei is the given name of Cai Yuanpei, a prominent Chinese educator and reformer who served as president of Peking University in the early 20th century.
  • D. Yuanzhen
    Yuanzhen was the Chinese era name used during the reign of Temür Khan, the second emperor of the Yuan dynasty.
  • E. Huangtong
    Huangtong was an era name used during the reign of Emperor Xizong of the Jurchen-led Jin dynasty in China.
  • 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: Tiānshū
Triple: [Book from the Sky, alsoKnownAs, Tiānshū]
Generated description
Tiānshū is an experimental Chinese artwork and book project by Xu Bing featuring thousands of invented, unreadable characters that resemble traditional Chinese script.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tiānshū
Target entity description: Tiānshū is an experimental Chinese artwork and book project by Xu Bing featuring thousands of invented, unreadable characters that resemble traditional Chinese script.
  • A. Shengzhi
    Shengzhi is the given name of Tang Shengzhi, a prominent Chinese Nationalist general active during the early 20th century.
  • B. Lishu
    Lishu is an ancient Chinese clerical script that emerged during the Qin and Han dynasties, marking a key transition from earlier seal scripts to more regular, standardized writing forms.
  • C. Yuanpei
    Yuanpei is the given name of Cai Yuanpei, a prominent Chinese educator and reformer who served as president of Peking University in the early 20th century.
  • D. Yuanzhen
    Yuanzhen was the Chinese era name used during the reign of Temür Khan, the second emperor of the Yuan dynasty.
  • E. Huangtong
    Huangtong was an era name used during the reign of Emperor Xizong of the Jurchen-led Jin dynasty in China.
  • 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_69d8dd040fb881909af2a964f65ad208 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d8057dec8190b9f1e0b54084ecec completed April 20, 2026, 7:38 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05c551e26c8190928642f451cb85f0 completed May 14, 2026, 12:51 p.m.
NEDg Description generation batch_6a05c7645d6c8190bd4d16b234c3384b completed May 14, 2026, 1 p.m.
NED2 Entity disambiguation (via description) batch_6a05c7c6e4148190bbdafd47ce2bdef4 completed May 14, 2026, 1:01 p.m.
Created at: April 10, 2026, 12:03 p.m.