Triple

T17178168
Position Surface form Disambiguated ID Type / Status
Subject Shanghai film industry E416913 entity
Predicate notableStar P4743 FINISHED
Object Hu Die
Hu Die was a celebrated Chinese silent film actress of the 1920s and 1930s, renowned as one of early Shanghai cinema’s most popular and influential stars.
E1254267 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: Hu Die | Statement: [Shanghai film industry, notableStar, Hu Die]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hu Die
Context triple: [Shanghai film industry, notableStar, Hu Die]
  • A. Han Duan
    Han Duan is a retired Chinese footballer and prolific forward who was a key player for the China women's national team and competed in multiple FIFA Women's World Cups and Olympic Games.
  • B. Chi Cheng
    Chi Cheng was an American musician best known as the original bassist for the alternative metal band Deftones.
  • C. Chin Han
    Chin Han is a Singaporean actor known for his roles in major Hollywood films such as The Dark Knight, Contagion, and Skyscraper.
  • D. He Zun
    He Zun is an ancient Western Zhou bronze ritual vessel renowned for bearing one of the earliest known inscriptions of the name “China” (Zhongguo).
  • E. Fan Ji
    Fan Ji was a consort of King Zhuang of Chu, a prominent ruler of the Spring and Autumn period in ancient 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: Hu Die
Triple: [Shanghai film industry, notableStar, Hu Die]
Generated description
Hu Die was a celebrated Chinese silent film actress of the 1920s and 1930s, renowned as one of early Shanghai cinema’s most popular and influential stars.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hu Die
Target entity description: Hu Die was a celebrated Chinese silent film actress of the 1920s and 1930s, renowned as one of early Shanghai cinema’s most popular and influential stars.
  • A. Han Duan
    Han Duan is a retired Chinese footballer and prolific forward who was a key player for the China women's national team and competed in multiple FIFA Women's World Cups and Olympic Games.
  • B. Chi Cheng
    Chi Cheng was an American musician best known as the original bassist for the alternative metal band Deftones.
  • C. Chin Han
    Chin Han is a Singaporean actor known for his roles in major Hollywood films such as The Dark Knight, Contagion, and Skyscraper.
  • D. He Zun
    He Zun is an ancient Western Zhou bronze ritual vessel renowned for bearing one of the earliest known inscriptions of the name “China” (Zhongguo).
  • E. Fan Ji
    Fan Ji was a consort of King Zhuang of Chu, a prominent ruler of the Spring and Autumn period in ancient 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_69d886d5f34c8190b24564dfaa63f3fb completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3fc0ee5008190a73875b39841fd9f completed April 18, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0148455afc8190931ba1316705ae0c completed May 11, 2026, 3:08 a.m.
NEDg Description generation batch_6a014a2f8fec8190b1303967a76ceb63 completed May 11, 2026, 3:17 a.m.
NED2 Entity disambiguation (via description) batch_6a014ab0be388190a6ce49cff469fe81 completed May 11, 2026, 3:19 a.m.
Created at: April 10, 2026, 5:37 a.m.