Triple
T22936974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sander Levin |
E569610
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Vicki Schlafer Levin
Vicki Schlafer Levin is the wife of longtime Michigan Democratic congressman Sander Levin and a member of the prominent Levin political family.
|
E1561729
|
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: Vicki Schlafer Levin | Statement: [Sander Levin, spouse, Vicki Schlafer Levin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vicki Schlafer Levin Context triple: [Sander Levin, spouse, Vicki Schlafer Levin]
-
A.
Judith Lerner
Judith Lerner is a character who appears in Jean-Luc Godard’s 2004 film "Notre musique."
-
B.
Gloria Nathanson
Gloria Nathanson was the wife of American novelist and poet Robert Nathan.
-
C.
Carol Nader
Carol Nader is an author and journalist best known for co-writing the non-fiction book *The Boy Who Wouldn’t Die*.
-
D.
Barbara Goldsmith
Barbara Goldsmith was an American author, journalist, and philanthropist known for her influential works of narrative history and her advocacy for human rights and freedom of expression.
-
E.
Janet Margolin
Janet Margolin was an American film and television actress best known for her roles in movies such as "David and Lisa" and Woody Allen's "Annie Hall."
- 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: Vicki Schlafer Levin Triple: [Sander Levin, spouse, Vicki Schlafer Levin]
Generated description
Vicki Schlafer Levin is the wife of longtime Michigan Democratic congressman Sander Levin and a member of the prominent Levin political family.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Vicki Schlafer Levin Target entity description: Vicki Schlafer Levin is the wife of longtime Michigan Democratic congressman Sander Levin and a member of the prominent Levin political family.
-
A.
Judith Lerner
Judith Lerner is a character who appears in Jean-Luc Godard’s 2004 film "Notre musique."
-
B.
Gloria Nathanson
Gloria Nathanson was the wife of American novelist and poet Robert Nathan.
-
C.
Carol Nader
Carol Nader is an author and journalist best known for co-writing the non-fiction book *The Boy Who Wouldn’t Die*.
-
D.
Barbara Goldsmith
Barbara Goldsmith was an American author, journalist, and philanthropist known for her influential works of narrative history and her advocacy for human rights and freedom of expression.
-
E.
Janet Margolin
Janet Margolin was an American film and television actress best known for her roles in movies such as "David and Lisa" and Woody Allen's "Annie Hall."
- 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_69e24590862c8190858f180ad302adab |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1813608e48190922df7a5386dc391 |
completed | April 29, 2026, 3:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0bc250aaa88190bd4d516e31012882 |
completed | May 19, 2026, 1:52 a.m. |
| NEDg | Description generation | batch_6a0bc30a16408190ba27d804c7a4933e |
completed | May 19, 2026, 1:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0bc39e4c00819083a5c7bc3c9c1526 |
completed | May 19, 2026, 1:57 a.m. |
Created at: April 17, 2026, 3:45 p.m.