Triple

T21150177
Position Surface form Disambiguated ID Type / Status
Subject 倪桂珍 E521166 entity
Predicate 子女 P980 FINISHED
Object 宋霭龄 — NE NERFINISHED

How this triple was built (2 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: 宋霭龄 | Statement: [倪桂珍, 子女, 宋霭龄]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 宋霭龄
Context triple: [倪桂珍, 子女, 宋霭龄]
  • A. 宋庆龄 chosen
    宋庆龄 was a prominent Chinese revolutionary and political leader, wife of Sun Yat-sen, and later one of the vice chairpersons and honorary presidents of the People’s Republic of China.
  • B. 宋子文
    宋子文 was a prominent Chinese banker and politician of the Republic of China era, known for serving as finance minister and premier and for his influential role in managing wartime finances and diplomacy.
  • C. T. V. Soong
    T. V. Soong was a prominent Chinese statesman and financier who served as a leading Nationalist government official and played a key diplomatic role for China during World War II.
  • D. 孔祥熙
    孔祥熙是中国近代著名的银行家和政治人物，曾在国民政府中担任财政部长等要职并深度参与当时的金融与经济政策制定。
  • E. Lucille Soong
    Lucille Soong is a Chinese-American actress known for her character roles in film and television, including appearances in movies like Freaky Friday and the TV series Fresh Off the Boat.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b50c6a848190a4e525a77a319b8a completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e72400911c8190978e88138a9bfaff completed April 21, 2026, 7:15 a.m.
Created at: April 16, 2026, 2:58 p.m.