Triple
T21395834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sidney Salkow |
E527776
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Marjorie Salkow
Marjorie Salkow was the wife of American film and television director Sidney Salkow.
|
E1528064
|
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: Marjorie Salkow | Statement: [Sidney Salkow, spouse, Marjorie Salkow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marjorie Salkow Context triple: [Sidney Salkow, spouse, Marjorie Salkow]
-
A.
Marjorie Hewitt Suchocki
Marjorie Hewitt Suchocki is an American theologian known for her influential work in process theology, feminist theology, and constructive Christian doctrine.
-
B.
Marjorie Wollenberg
Marjorie Wollenberg, better known by her stage name Marjorie Lord, was an American actress best remembered for her role as Kathy Williams on the classic television sitcom "Make Room for Daddy."
-
C.
Marjorie Fried
Marjorie Fried was the wife of Nobel Prize–winning geneticist George W. Beadle.
-
D.
Marjorie Margolies
Marjorie Margolies is an American journalist, author, and former U.S. Congresswoman from Pennsylvania.
-
E.
Sylvia Rosen
Sylvia Rosen is a neighbor and love interest of Don Draper in the television series "Mad Men," known for their clandestine affair and its impact on his personal life.
- 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: Marjorie Salkow Triple: [Sidney Salkow, spouse, Marjorie Salkow]
Generated description
Marjorie Salkow was the wife of American film and television director Sidney Salkow.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marjorie Salkow Target entity description: Marjorie Salkow was the wife of American film and television director Sidney Salkow.
-
A.
Marjorie Hewitt Suchocki
Marjorie Hewitt Suchocki is an American theologian known for her influential work in process theology, feminist theology, and constructive Christian doctrine.
-
B.
Marjorie Wollenberg
Marjorie Wollenberg, better known by her stage name Marjorie Lord, was an American actress best remembered for her role as Kathy Williams on the classic television sitcom "Make Room for Daddy."
-
C.
Marjorie Fried
Marjorie Fried was the wife of Nobel Prize–winning geneticist George W. Beadle.
-
D.
Marjorie Margolies
Marjorie Margolies is an American journalist, author, and former U.S. Congresswoman from Pennsylvania.
-
E.
Sylvia Rosen
Sylvia Rosen is a neighbor and love interest of Don Draper in the television series "Mad Men," known for their clandestine affair and its impact on his personal life.
- 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_69e0b51ff3748190935c0a513c62a12b |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69ee62ce3c5c81909e1e584e2f6667c8 |
completed | April 26, 2026, 7:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0abc87cab08190b9a5457ba9868784 |
completed | May 18, 2026, 7:15 a.m. |
| NEDg | Description generation | batch_6a0abd6207688190ab6ba1a04fa663a7 |
completed | May 18, 2026, 7:18 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0abe80fe7c8190a648efabc360b06d |
completed | May 18, 2026, 7:23 a.m. |
Created at: April 16, 2026, 5:13 p.m.