Triple
T3206567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kristen Wiig |
E67174
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Avi Rothman
Avi Rothman is an American actor, writer, and comedian known for his work in film and television and for being married to actress and comedian Kristen Wiig.
|
E420739
|
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: Avi Rothman | Statement: [Kristen Wiig, spouse, Avi Rothman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Avi Rothman Context triple: [Kristen Wiig, spouse, Avi Rothman]
-
A.
Avi Lerner
Avi Lerner is an Israeli-American film producer and founder of Millennium Films, known for financing and producing numerous action movies and franchises.
-
B.
Ryan Roslansky
Ryan Roslansky is the CEO of LinkedIn, known for leading the professional networking platform’s product and business strategy.
-
C.
Nathan Grossman
Nathan Grossman is a Swedish documentary filmmaker best known for directing the climate activist portrait film "I Am Greta."
-
D.
Jay Shofet
Jay Shofet is an Israeli environmental advocate and sustainability professional known for his work in conservation and public policy.
-
E.
Jay Rabinowitz
Jay Rabinowitz is a film editor known for his work on numerous feature films, including the science-fiction thriller "The Adjustment Bureau."
- 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: Avi Rothman Triple: [Kristen Wiig, spouse, Avi Rothman]
Generated description
Avi Rothman is an American actor, writer, and comedian known for his work in film and television and for being married to actress and comedian Kristen Wiig.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Avi Rothman Target entity description: Avi Rothman is an American actor, writer, and comedian known for his work in film and television and for being married to actress and comedian Kristen Wiig.
-
A.
Avi Lerner
Avi Lerner is an Israeli-American film producer and founder of Millennium Films, known for financing and producing numerous action movies and franchises.
-
B.
Ryan Roslansky
Ryan Roslansky is the CEO of LinkedIn, known for leading the professional networking platform’s product and business strategy.
-
C.
Nathan Grossman
Nathan Grossman is a Swedish documentary filmmaker best known for directing the climate activist portrait film "I Am Greta."
-
D.
Jay Shofet
Jay Shofet is an Israeli environmental advocate and sustainability professional known for his work in conservation and public policy.
-
E.
Jay Rabinowitz
Jay Rabinowitz is a film editor known for his work on numerous feature films, including the science-fiction thriller "The Adjustment Bureau."
- 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_69ad8589bd988190afa7ed2bdffb7b33 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaa56c21c8190b6aa7c56cb15ad56 |
completed | March 8, 2026, 4:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b589b1574c8190a7cd897febdbdbe5 |
completed | March 14, 2026, 4:15 p.m. |
| NEDg | Description generation | batch_69b58df59b3081909c0654334c37c8df |
completed | March 14, 2026, 4:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b58e44bf8081909933afb1482723e7 |
completed | March 14, 2026, 4:35 p.m. |
Created at: March 8, 2026, 3:07 p.m.