Triple

T10974126
Position Surface form Disambiguated ID Type / Status
Subject Joan Collins E259323 entity
Predicate spouse P13 FINISHED
Object Ron Kass
Ron Kass was a music industry executive and film producer best known for his work with Apple Records and for being married to actress Joan Collins.
E896873 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: Ron Kass | Statement: [Joan Collins, spouse, Ron Kass]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ron Kass
Context triple: [Joan Collins, spouse, Ron Kass]
  • A. Jeffrey Cohen
    Jeffrey Cohen is a songwriter best known for co-writing the theme song to the James Bond film "Licence to Kill."
  • B. Paul Kahn
    Paul Kahn is a notable individual whose specific public recognition or field of prominence is not clearly identifiable from the given information.
  • C. Allen Rivkin
    Allen Rivkin was an American screenwriter active during Hollywood’s studio era, known for his work on numerous mid-20th-century films.
  • D. Michael D. Rosenthal
    Michael D. Rosenthal is a writer best known as the author whose work inspired the "Twilight Zone" episode "A Kind of Stopwatch."
  • E. John Kahn
    John Kahn was an American bassist and producer best known for his long-running collaboration with Jerry Garcia across multiple projects.
  • 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: Ron Kass
Triple: [Joan Collins, spouse, Ron Kass]
Generated description
Ron Kass was a music industry executive and film producer best known for his work with Apple Records and for being married to actress Joan Collins.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ron Kass
Target entity description: Ron Kass was a music industry executive and film producer best known for his work with Apple Records and for being married to actress Joan Collins.
  • A. Jeffrey Cohen
    Jeffrey Cohen is a songwriter best known for co-writing the theme song to the James Bond film "Licence to Kill."
  • B. Paul Kahn
    Paul Kahn is a notable individual whose specific public recognition or field of prominence is not clearly identifiable from the given information.
  • C. Allen Rivkin
    Allen Rivkin was an American screenwriter active during Hollywood’s studio era, known for his work on numerous mid-20th-century films.
  • D. Michael D. Rosenthal
    Michael D. Rosenthal is a writer best known as the author whose work inspired the "Twilight Zone" episode "A Kind of Stopwatch."
  • E. John Kahn
    John Kahn was an American bassist and producer best known for his long-running collaboration with Jerry Garcia across multiple projects.
  • 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_69d6aa895f4c8190887a15460ef622f4 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d771f3794c8190b1992b4695139b62 completed April 9, 2026, 9:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2d7aeb66c8190b9d18642b2ad2ea0 completed April 18, 2026, 1 a.m.
NEDg Description generation batch_69e2ff211ae88190a40380cd25a61812 completed April 18, 2026, 3:48 a.m.
NED2 Entity disambiguation (via description) batch_69e32634397481908284c04448274b25 completed April 18, 2026, 6:35 a.m.
Created at: April 8, 2026, 9:24 p.m.