Triple

T16536847
Position Surface form Disambiguated ID Type / Status
Subject Donald Rubin E401713 entity
Predicate spouse P13 FINISHED
Object Shelly Rubin
Shelly Rubin is known as the wife of prominent statistician Donald Rubin, a leading figure in causal inference and missing data analysis.
 E391994 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: Shelly Rubin | Statement: [Donald Rubin, spouse, Shelly Rubin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shelly Rubin
Context triple: [Donald Rubin, spouse, Shelly Rubin]
  • A. Shelly Rubin
    Shelly Rubin is an American philanthropist and arts patron best known as a co-founder of the Rubin Museum of Art in New York City.
  • B. Risa Shapiro
    Risa Shapiro is a film producer best known for her work on the 1993 crime thriller "Kalifornia."
  • C. Shelly Kaplow
    Shelly Kaplow is a down-on-his-luck casino "cooler" whose mere presence is believed to jinx gamblers in the 2003 film *The Cooler*.
  • D. Shelly Pfefferman
    Shelly Pfefferman is a central character in the television series "Transparent," portrayed as the outspoken, emotionally complex matriarch of the Pfefferman family.
  • E. Jacqueline Shapiro
    Jacqueline Shapiro is known primarily as the wife of American screenwriter and producer Ernest Lehman.
  • 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: Shelly Rubin
Triple: [Donald Rubin, spouse, Shelly Rubin]
Generated description
Shelly Rubin is known as the wife of prominent statistician Donald Rubin, a leading figure in causal inference and missing data analysis.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shelly Rubin
Target entity description: Shelly Rubin is known as the wife of prominent statistician Donald Rubin, a leading figure in causal inference and missing data analysis.
  • A. Shelly Rubin chosen
    Shelly Rubin is an American philanthropist and arts patron best known as a co-founder of the Rubin Museum of Art in New York City.
  • B. Risa Shapiro
    Risa Shapiro is a film producer best known for her work on the 1993 crime thriller "Kalifornia."
  • C. Shelly Kaplow
    Shelly Kaplow is a down-on-his-luck casino "cooler" whose mere presence is believed to jinx gamblers in the 2003 film *The Cooler*.
  • D. Shelly Pfefferman
    Shelly Pfefferman is a central character in the television series "Transparent," portrayed as the outspoken, emotionally complex matriarch of the Pfefferman family.
  • E. Jacqueline Shapiro
    Jacqueline Shapiro is known primarily as the wife of American screenwriter and producer Ernest Lehman.
  • F. None of above.

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_69d88384bc30819084229e7dcdc39a41 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e34558ec448190a6dcc15d62d1889c completed April 18, 2026, 8:48 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0491547b9081909876f88fe6a58ee7 completed May 13, 2026, 2:57 p.m.
NEDg Description generation batch_6a04922aa908819093d00f57fdb00627 completed May 13, 2026, 3 p.m.
NED2 Entity disambiguation (via description) batch_6a04933727488190b7a04789a17a16a0 completed May 13, 2026, 3:05 p.m.
Created at: April 10, 2026, 5:15 a.m.