Triple
T23031797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johnny Tsunami |
E573479
|
entity |
| Predicate | starredActor |
P5563
|
FINISHED |
| Object |
Mary Page Keller
Mary Page Keller is an American actress known for her work in television sitcoms and family-oriented films, including roles in series like "Duet" and "Baby Talk."
|
E1588207
|
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: Mary Page Keller | Statement: [Johnny Tsunami, starredActor, Mary Page Keller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Page Keller Context triple: [Johnny Tsunami, starredActor, Mary Page Keller]
-
A.
Dorothy Davenport
Dorothy Davenport was an American silent film actress, director, and producer known for her socially conscious films in the early 20th century.
-
B.
Mary Kenner
Mary Kenner was the wife of noted literary critic and scholar Hugh Kenner.
-
C.
Margaret Huston
Margaret Huston is known primarily as the wife of James Ramsay.
-
D.
Marjorie Hearn
Marjorie Hearn was the longtime wife and partner of legendary Los Angeles Lakers broadcaster Chick Hearn.
-
E.
Dorothy McKim
Dorothy McKim is an American film producer best known for her work on Disney animated features and shorts, including projects like "Meet the Robinsons."
- 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: Mary Page Keller Triple: [Johnny Tsunami, starredActor, Mary Page Keller]
Generated description
Mary Page Keller is an American actress known for her work in television sitcoms and family-oriented films, including roles in series like "Duet" and "Baby Talk."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mary Page Keller Target entity description: Mary Page Keller is an American actress known for her work in television sitcoms and family-oriented films, including roles in series like "Duet" and "Baby Talk."
-
A.
Dorothy Davenport
Dorothy Davenport was an American silent film actress, director, and producer known for her socially conscious films in the early 20th century.
-
B.
Mary Kenner
Mary Kenner was the wife of noted literary critic and scholar Hugh Kenner.
-
C.
Margaret Huston
Margaret Huston is known primarily as the wife of James Ramsay.
-
D.
Marjorie Hearn
Marjorie Hearn was the longtime wife and partner of legendary Los Angeles Lakers broadcaster Chick Hearn.
-
E.
Dorothy McKim
Dorothy McKim is an American film producer best known for her work on Disney animated features and shorts, including projects like "Meet the Robinsons."
- 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_69e245b911188190bc3d96326c847969 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f184822a90819081907d72c76770b0 |
completed | April 29, 2026, 4:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c822d73608190bce952f3768f8cb1 |
completed | May 19, 2026, 3:30 p.m. |
| NEDg | Description generation | batch_6a0ca6eda1f481908482f3a66d576c3c |
completed | May 19, 2026, 6:07 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ca7c5176c81908221307bb50ff4ed |
completed | May 19, 2026, 6:11 p.m. |
Created at: April 17, 2026, 3:53 p.m.