Triple

T3376682
Position Surface form Disambiguated ID Type / Status
Subject Robert Downey Sr. E71081 entity
Predicate spouse P13 FINISHED
Object Laura Ernst
Laura Ernst was the second wife of filmmaker Robert Downey Sr., known primarily for her connection to the Downey family.
E443548 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: Laura Ernst | Statement: [Robert Downey Sr., spouse, Laura Ernst]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laura Ernst
Context triple: [Robert Downey Sr., spouse, Laura Ernst]
  • A. Lisa Eilbacher
    Lisa Eilbacher is an American actress best known for her roles in 1980s films and television series, including prominent appearances in action and drama movies.
  • B. Stefanie Ehrlich
    Stefanie Ehrlich is known as a child of the prominent American biologist and author Paul Ehrlich.
  • C. Elizabeth Kolb
    Elizabeth Kolb was the woman who served as the ceremonial sponsor for the U.S. Navy battleship USS Pennsylvania (BB-38) at its launching.
  • D. Laura Hastings-Smith
    Laura Hastings-Smith is a British film and television producer known for working on acclaimed projects including the 2015 adaptation of Macbeth.
  • E. Karen Rosenfelt
    Karen Rosenfelt is an American film producer known for her work on major studio franchises and popular young adult adaptations, including entries in the Twilight series.
  • 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: Laura Ernst
Triple: [Robert Downey Sr., spouse, Laura Ernst]
Generated description
Laura Ernst was the second wife of filmmaker Robert Downey Sr., known primarily for her connection to the Downey family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Laura Ernst
Target entity description: Laura Ernst was the second wife of filmmaker Robert Downey Sr., known primarily for her connection to the Downey family.
  • A. Lisa Eilbacher
    Lisa Eilbacher is an American actress best known for her roles in 1980s films and television series, including prominent appearances in action and drama movies.
  • B. Stefanie Ehrlich
    Stefanie Ehrlich is known as a child of the prominent American biologist and author Paul Ehrlich.
  • C. Elizabeth Kolb
    Elizabeth Kolb was the woman who served as the ceremonial sponsor for the U.S. Navy battleship USS Pennsylvania (BB-38) at its launching.
  • D. Laura Hastings-Smith
    Laura Hastings-Smith is a British film and television producer known for working on acclaimed projects including the 2015 adaptation of Macbeth.
  • E. Karen Rosenfelt
    Karen Rosenfelt is an American film producer known for her work on major studio franchises and popular young adult adaptations, including entries in the Twilight series.
  • 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_69ad85a7f80c8190a05e43013f298942 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb2e776508190bc123fb17b36f062 completed March 8, 2026, 5:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69b636ee2ed88190b37c7f6027d7623b completed March 15, 2026, 4:34 a.m.
NEDg Description generation batch_69b6379d22448190976a84a18cf85ca6 completed March 15, 2026, 4:37 a.m.
NED2 Entity disambiguation (via description) batch_69b638b105e88190a02c515a3416a026 completed March 15, 2026, 4:42 a.m.
Created at: March 8, 2026, 3:13 p.m.