Triple
T17687906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Ewell |
E440942
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Martha Wyler
Martha Wyler was the wife of American actor Tom Ewell, known for his work in mid-20th-century film and theater.
|
E1282796
|
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: Martha Wyler | Statement: [Tom Ewell, spouse, Martha Wyler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Martha Wyler Context triple: [Tom Ewell, spouse, Martha Wyler]
-
A.
Catherine Wyler
Catherine Wyler is an American film producer and arts administrator known for her work on classic film preservation and for producing projects such as the 1989 film "Memphis Belle."
-
B.
Beatrice DeMille
Beatrice DeMille was an American playwright and literary agent best known as the mother of pioneering film director Cecil B. DeMille.
-
C.
Lili Fini Zanuck
Lili Fini Zanuck is an American film producer and director best known for her Academy Award–winning work on the 1989 film "Driving Miss Daisy."
-
D.
Freda W. Sandrich
Freda W. Sandrich was the wife of American film director and producer Mark Sandrich, associated with Hollywood’s classic era.
-
E.
Katherine DeMille
Katherine DeMille was a Canadian-born American film actress of the 1930s and 1940s who appeared in numerous Hollywood productions.
- 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: Martha Wyler Triple: [Tom Ewell, spouse, Martha Wyler]
Generated description
Martha Wyler was the wife of American actor Tom Ewell, known for his work in mid-20th-century film and theater.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Martha Wyler Target entity description: Martha Wyler was the wife of American actor Tom Ewell, known for his work in mid-20th-century film and theater.
-
A.
Catherine Wyler
Catherine Wyler is an American film producer and arts administrator known for her work on classic film preservation and for producing projects such as the 1989 film "Memphis Belle."
-
B.
Beatrice DeMille
Beatrice DeMille was an American playwright and literary agent best known as the mother of pioneering film director Cecil B. DeMille.
-
C.
Lili Fini Zanuck
Lili Fini Zanuck is an American film producer and director best known for her Academy Award–winning work on the 1989 film "Driving Miss Daisy."
-
D.
Freda W. Sandrich
Freda W. Sandrich was the wife of American film director and producer Mark Sandrich, associated with Hollywood’s classic era.
-
E.
Katherine DeMille
Katherine DeMille was a Canadian-born American film actress of the 1930s and 1940s who appeared in numerous Hollywood productions.
- 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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4704944d8819089b153aa14839fc0 |
completed | April 19, 2026, 6:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a02232e1b4481908e8a89f2c1c244f1 |
completed | May 11, 2026, 6:42 p.m. |
| NEDg | Description generation | batch_6a0224e2403881909a6f86bcad4ce7b3 |
completed | May 11, 2026, 6:50 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a02254cbd3c8190afca986f066a60d2 |
completed | May 11, 2026, 6:51 p.m. |
Created at: April 10, 2026, 10:03 a.m.