Triple

T1204410
Position Surface form Disambiguated ID Type / Status
Subject Joseph L. Mankiewicz E25854 entity
Predicate spouse P13 FINISHED
Object Elizabeth Young
Elizabeth Young was an American actress active in the 1930s who appeared in several Hollywood films before retiring from the screen.
 E138011 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: Elizabeth Young | Statement: [Joseph L. Mankiewicz, spouse, Elizabeth Young]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Elizabeth Young
Context triple: [Joseph L. Mankiewicz, spouse, Elizabeth Young]
  • A. Margo King
    Margo King is a notable individual distinguished enough to be recognized as a prominent bearer of the surname King.
  • B. Laura Marling
    Laura Marling is an English folk singer-songwriter and guitarist acclaimed for her introspective lyrics and distinctive, mature vocal style.
  • C. Sarah Wildes
    Sarah Wildes was a woman executed for witchcraft during the Salem witch trials in 1692.
  • D. Sarah Jane Emery
    Sarah Jane Emery was the wife of Hannibal Hamlin, who served as vice president of the United States under Abraham Lincoln.
  • E. Syd Cassyd
    Syd Cassyd was an American television executive and visionary best known for founding the International Academy of Television Arts & Sciences, which administers the International Emmy Awards.
  • 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: Elizabeth Young
Triple: [Joseph L. Mankiewicz, spouse, Elizabeth Young]
Generated description
Elizabeth Young was an American actress active in the 1930s who appeared in several Hollywood films before retiring from the screen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Elizabeth Young
Target entity description: Elizabeth Young was an American actress active in the 1930s who appeared in several Hollywood films before retiring from the screen.
  • A. Margo King
    Margo King is a notable individual distinguished enough to be recognized as a prominent bearer of the surname King.
  • B. Laura Marling
    Laura Marling is an English folk singer-songwriter and guitarist acclaimed for her introspective lyrics and distinctive, mature vocal style.
  • C. Sarah Wildes
    Sarah Wildes was a woman executed for witchcraft during the Salem witch trials in 1692.
  • D. Sarah Jane Emery
    Sarah Jane Emery was the wife of Hannibal Hamlin, who served as vice president of the United States under Abraham Lincoln.
  • E. Syd Cassyd
    Syd Cassyd was an American television executive and visionary best known for founding the International Academy of Television Arts & Sciences, which administers the International Emmy Awards.
  • 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_69a4942b30f08190a91c60573e16b5ef completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bdbf94188190991f63a84cc76b8a completed March 1, 2026, 10:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac7f3caed481908e9e4b6b9daa544d completed March 7, 2026, 7:40 p.m.
NEDg Description generation batch_69ac7fa90f608190bec0c7dff1d7c9ae completed March 7, 2026, 7:42 p.m.
NED2 Entity disambiguation (via description) batch_69ac808a919081908253d1778695ab2d completed March 7, 2026, 7:46 p.m.
Created at: March 1, 2026, 7:46 p.m.