Triple
T7974677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lisa Bonet |
E185413
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object |
Arlene Litman
Arlene Litman was the mother of American actress Lisa Bonet.
|
E720087
|
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: Arlene Litman | Statement: [Lisa Bonet, parent, Arlene Litman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arlene Litman Context triple: [Lisa Bonet, parent, Arlene Litman]
-
A.
Judy Levitt
Judy Levitt is an American actress best known for her long marriage to Star Trek actor Walter Koenig and for appearing in several of his film and television projects.
-
B.
Susan Littenberg
Susan Littenberg is a film editor known for her work on feature films such as the teen comedy "Easy A."
-
C.
Ann Biderman
Ann Biderman is an American screenwriter and television creator known for her work on crime dramas such as the film "Public Enemies" and the TV series "Southland" and "Ray Donovan."
-
D.
Ilene Rosenzweig
Ilene Rosenzweig is a writer and editor best known for co-authoring lifestyle and design books with fashion designer Cynthia Rowley.
-
E.
Barbara Siegel
Barbara Siegel is an American author best known for co-writing numerous science fiction and fantasy novels and game-related books, often in collaboration with her husband Scott Siegel.
- 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: Arlene Litman Triple: [Lisa Bonet, parent, Arlene Litman]
Generated description
Arlene Litman was the mother of American actress Lisa Bonet.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Arlene Litman Target entity description: Arlene Litman was the mother of American actress Lisa Bonet.
-
A.
Judy Levitt
Judy Levitt is an American actress best known for her long marriage to Star Trek actor Walter Koenig and for appearing in several of his film and television projects.
-
B.
Susan Littenberg
Susan Littenberg is a film editor known for her work on feature films such as the teen comedy "Easy A."
-
C.
Ann Biderman
Ann Biderman is an American screenwriter and television creator known for her work on crime dramas such as the film "Public Enemies" and the TV series "Southland" and "Ray Donovan."
-
D.
Ilene Rosenzweig
Ilene Rosenzweig is a writer and editor best known for co-authoring lifestyle and design books with fashion designer Cynthia Rowley.
-
E.
Barbara Siegel
Barbara Siegel is an American author best known for co-writing numerous science fiction and fantasy novels and game-related books, often in collaboration with her husband Scott Siegel.
- 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_69ca829851908190b4e03829353ee7c3 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3bf42a508190bb661fce34ec0151 |
completed | March 31, 2026, 3:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd33e50f0c81909c96da2d78f17ffd |
completed | April 1, 2026, 3:04 p.m. |
| NEDg | Description generation | batch_69cd36ecc1d88190a978f1d51b0e1382 |
completed | April 1, 2026, 3:17 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cd4e7822e48190bb573162f224bd8c |
completed | April 1, 2026, 4:57 p.m. |
Created at: March 30, 2026, 5:14 p.m.