Triple

T21978177
Position Surface form Disambiguated ID Type / Status
Subject Dick Foran E542763 entity
Predicate spouse P13 FINISHED
Object Susanne Rosser
Susanne Rosser is known as the spouse of American actor and singer Dick Foran.
E1535332 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: Susanne Rosser | Statement: [Dick Foran, spouse, Susanne Rosser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susanne Rosser
Context triple: [Dick Foran, spouse, Susanne Rosser]
  • A. Suzanne Martin
    Suzanne Martin is an American television writer and producer best known for creating the sitcom "Hot in Cleveland."
  • B. Suzanne Scott
    Suzanne Scott is an individual honored as a namesake of the Suzanne and Walter Scott Aquarium, indicating her significant personal or philanthropic connection to that institution.
  • C. Suzanne Mulkern
    Suzanne Mulkern is known for being the first wife of Apple co-founder Steve Wozniak.
  • D. Suzanne Frank
    Suzanne Frank is the private client for Peter Eisenman’s experimental House VI residence, a landmark of deconstructivist architecture.
  • E. Suzanne Todd
    Suzanne Todd is an American film producer known for her work on influential movies such as "Memento" and the "Austin Powers" 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: Susanne Rosser
Triple: [Dick Foran, spouse, Susanne Rosser]
Generated description
Susanne Rosser is known as the spouse of American actor and singer Dick Foran.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Susanne Rosser
Target entity description: Susanne Rosser is known as the spouse of American actor and singer Dick Foran.
  • A. Suzanne Martin
    Suzanne Martin is an American television writer and producer best known for creating the sitcom "Hot in Cleveland."
  • B. Suzanne Scott
    Suzanne Scott is an individual honored as a namesake of the Suzanne and Walter Scott Aquarium, indicating her significant personal or philanthropic connection to that institution.
  • C. Suzanne Mulkern
    Suzanne Mulkern is known for being the first wife of Apple co-founder Steve Wozniak.
  • D. Suzanne Frank
    Suzanne Frank is the private client for Peter Eisenman’s experimental House VI residence, a landmark of deconstructivist architecture.
  • E. Suzanne Todd
    Suzanne Todd is an American film producer known for her work on influential movies such as "Memento" and the "Austin Powers" 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_69e0c48070988190909db97667b9a0ac completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1248a60708190a9aa8b9b7738c261 completed April 28, 2026, 9:20 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0af0c93f608190bad457a860e122be completed May 18, 2026, 10:58 a.m.
NEDg Description generation batch_6a0af20dd3c88190a059ede31daa9c6d completed May 18, 2026, 11:03 a.m.
NED2 Entity disambiguation (via description) batch_6a0af29431648190a506d5e1a4fc9ce7 completed May 18, 2026, 11:05 a.m.
Created at: April 16, 2026, 8:03 p.m.