Triple

T12498625
Position Surface form Disambiguated ID Type / Status
Subject Otto Preminger E298754 entity
Predicate spouse P13 FINISHED
Object Hope Bryce
Hope Bryce was the wife of influential Austrian-American film director and producer Otto Preminger.
E987786 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: Hope Bryce | Statement: [Otto Preminger, spouse, Hope Bryce]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hope Bryce
Context triple: [Otto Preminger, spouse, Hope Bryce]
  • A. Haley Jones
    Haley Jones is an American basketball player best known for starring at Stanford University, where she led the Cardinal to a national championship and emerged as one of the top collegiate guards in the country.
  • B. Bailey Moore
    Bailey Moore is a local political leader serving as the mayor of Allen, Texas.
  • C. Haley P. Douglass
    Haley P. Douglass is a graduate of Wilberforce University, a historically Black university known for its emphasis on liberal arts and leadership development.
  • D. Reese Hays
    Reese Hays is a composer best known for creating the iconic theme music used in NFL on Fox broadcasts.
  • E. Mallory Hanson
    Mallory Hanson is a central supporting character in the comedy series "Grace and Frankie," known as one of Grace's daughters who often juggles family responsibilities and personal ambitions.
  • 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: Hope Bryce
Triple: [Otto Preminger, spouse, Hope Bryce]
Generated description
Hope Bryce was the wife of influential Austrian-American film director and producer Otto Preminger.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hope Bryce
Target entity description: Hope Bryce was the wife of influential Austrian-American film director and producer Otto Preminger.
  • A. Haley Jones
    Haley Jones is an American basketball player best known for starring at Stanford University, where she led the Cardinal to a national championship and emerged as one of the top collegiate guards in the country.
  • B. Bailey Moore
    Bailey Moore is a local political leader serving as the mayor of Allen, Texas.
  • C. Haley P. Douglass
    Haley P. Douglass is a graduate of Wilberforce University, a historically Black university known for its emphasis on liberal arts and leadership development.
  • D. Reese Hays
    Reese Hays is a composer best known for creating the iconic theme music used in NFL on Fox broadcasts.
  • E. Mallory Hanson
    Mallory Hanson is a central supporting character in the comedy series "Grace and Frankie," known as one of Grace's daughters who often juggles family responsibilities and personal ambitions.
  • 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_69d6ada4cd388190ae3bbf83ff87057a completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94dfa98348190b9ac164ecdada6fe completed April 10, 2026, 7:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bb131608190b34a07a7026b160e completed May 2, 2026, 7:08 p.m.
NEDg Description generation batch_69f64d15a97c81909046190f0d0fd986 completed May 2, 2026, 7:14 p.m.
NED2 Entity disambiguation (via description) batch_69f64e6d311c8190b851b89e394165d0 completed May 2, 2026, 7:20 p.m.
Created at: April 8, 2026, 9:57 p.m.