Triple

T14830171
Position Surface form Disambiguated ID Type / Status
Subject Zhongshan Park (Beijing) E348677 entity
Predicate hasFormerName P65 FINISHED
Object Shejitan
Shejitan is the historic Imperial Altar of Earth and Harvests in Beijing, originally used for state rituals during the Ming and Qing dynasties.
E1122265 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: Shejitan | Statement: [Zhongshan Park (Beijing), hasFormerName, Shejitan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shejitan
Context triple: [Zhongshan Park (Beijing), hasFormerName, Shejitan]
  • A. Shuja
    Shuja is a given name most notably associated with Shuja Shah Durrani, a 19th-century ruler of the Durrani Empire in Afghanistan.
  • B. Sejnane
    Sejnane is a town in northern Tunisia known for its traditional handmade pottery and rural landscapes.
  • C. Shekini
    Shekini is a popular Afrobeat/dancehall song by Nigerian music duo P-Square known for its energetic rhythm and club-friendly vibe.
  • D. Sindalah
    Sindalah is a luxury island destination in Saudi Arabia’s NEOM mega-development, designed as an exclusive hub for high-end tourism, yachting, and leisure on the Red Sea.
  • E. Sa'ir
    Sa'ir is a Palestinian town located in the southern West Bank, northeast of Hebron.
  • 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: Shejitan
Triple: [Zhongshan Park (Beijing), hasFormerName, Shejitan]
Generated description
Shejitan is the historic Imperial Altar of Earth and Harvests in Beijing, originally used for state rituals during the Ming and Qing dynasties.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Shejitan
Target entity description: Shejitan is the historic Imperial Altar of Earth and Harvests in Beijing, originally used for state rituals during the Ming and Qing dynasties.
  • A. Shuja
    Shuja is a given name most notably associated with Shuja Shah Durrani, a 19th-century ruler of the Durrani Empire in Afghanistan.
  • B. Sejnane
    Sejnane is a town in northern Tunisia known for its traditional handmade pottery and rural landscapes.
  • C. Shekini
    Shekini is a popular Afrobeat/dancehall song by Nigerian music duo P-Square known for its energetic rhythm and club-friendly vibe.
  • D. Sindalah
    Sindalah is a luxury island destination in Saudi Arabia’s NEOM mega-development, designed as an exclusive hub for high-end tourism, yachting, and leisure on the Red Sea.
  • E. Sa'ir
    Sa'ir is a Palestinian town located in the southern West Bank, northeast of Hebron.
  • 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_69d822ec69008190a9232caa68836872 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded0748eec8190a39c94024c3a3e3e completed April 14, 2026, 11:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe38a16fd881909d246d8d1811a673 completed May 8, 2026, 7:25 p.m.
NEDg Description generation batch_69fe502938dc8190892373403077cfdd completed May 8, 2026, 9:05 p.m.
NED2 Entity disambiguation (via description) batch_69fe509a02c08190bd2171b16584cd64 completed May 8, 2026, 9:07 p.m.
Created at: April 10, 2026, 1:51 a.m.