Triple

T17641556
Position Surface form Disambiguated ID Type / Status
Subject Aram Saroyan E429240 entity
Predicate spouse P13 FINISHED
Object Gailyn Saroyan (divorced)
Gailyn Saroyan is the former wife of American poet and writer Aram Saroyan.
 E1278831 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: Gailyn Saroyan (divorced) | Statement: [Aram Saroyan, spouse, Gailyn Saroyan (divorced)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gailyn Saroyan (divorced)
Context triple: [Aram Saroyan, spouse, Gailyn Saroyan (divorced)]
  • A. Cherilyn Sarkisian
    Cherilyn Sarkisian, better known as Cher, is an American singer, actress, and pop culture icon often called the "Goddess of Pop" for her decades-long influence on music, film, and fashion.
  • B. Janis Sarkisian
    Janis Sarkisian is a sharp-witted, artsy outsider and one of the central protagonists in the Mean Girls musical, known for her rebellious spirit and critique of high school social hierarchies.
  • C. Dawni Sahanovitch
    Dawni Sahanovitch is a Canadian producer and production manager known for her work in film and television and for being married to actor Devon Sawa.
  • D. Betsy Gaghan
    Betsy Gaghan is the daughter of American screenwriter and director Stephen Gaghan.
  • E. Evangeline Mardirosian
    Evangeline Mardirosian is a film producer known for her co-producing work on the movie "Daytona."
  • 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: Gailyn Saroyan (divorced)
Triple: [Aram Saroyan, spouse, Gailyn Saroyan (divorced)]
Generated description
Gailyn Saroyan is the former wife of American poet and writer Aram Saroyan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gailyn Saroyan (divorced)
Target entity description: Gailyn Saroyan is the former wife of American poet and writer Aram Saroyan.
  • A. Cherilyn Sarkisian
    Cherilyn Sarkisian, better known as Cher, is an American singer, actress, and pop culture icon often called the "Goddess of Pop" for her decades-long influence on music, film, and fashion.
  • B. Janis Sarkisian
    Janis Sarkisian is a sharp-witted, artsy outsider and one of the central protagonists in the Mean Girls musical, known for her rebellious spirit and critique of high school social hierarchies.
  • C. Dawni Sahanovitch
    Dawni Sahanovitch is a Canadian producer and production manager known for her work in film and television and for being married to actor Devon Sawa.
  • D. Betsy Gaghan
    Betsy Gaghan is the daughter of American screenwriter and director Stephen Gaghan.
  • E. Evangeline Mardirosian
    Evangeline Mardirosian is a film producer known for her co-producing work on the movie "Daytona."
  • 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_69d889e2c2608190b762e76d9b2262f1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46de645208190a40dcf443f8afd82 completed April 19, 2026, 5:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a020aa7be948190bf0ab64a2908d3b1 completed May 11, 2026, 4:58 p.m.
NEDg Description generation batch_6a020b51c208819083b1634221929628 completed May 11, 2026, 5:01 p.m.
NED2 Entity disambiguation (via description) batch_6a020bd466d881909ffdfe3cf932b980 completed May 11, 2026, 5:03 p.m.
Created at: April 10, 2026, 6:03 a.m.