Triple
T19891946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Borzage |
E478052
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Borzage
Borzage is a surname most notably associated with Frank Borzage, an influential American film director and Academy Award winner of Hollywood’s early sound era.
|
E1400551
|
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: Borzage | Statement: [Frank Borzage, familyName, Borzage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Borzage Context triple: [Frank Borzage, familyName, Borzage]
-
A.
Modjeski
Modjeski is the surname of Ralph Modjeski, a prominent Polish-American civil engineer renowned for designing major bridges in the United States.
-
B.
Lorre
Lorre is a surname most notably associated with Hungarian-American actor Peter Lorre and his family.
-
C.
Bela Pratt
Bela Pratt was an American sculptor known for his public monuments and architectural sculptures, particularly in Boston and other U.S. cities.
-
D.
Mary Bogdanovich
Mary Bogdanovich is known as the spouse of American actor and film producer Brad Dexter.
-
E.
Lecy Goranson
Lecy Goranson is an American actress best known for playing Becky Conner on the sitcom "Roseanne" and its revival.
- 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: Borzage Triple: [Frank Borzage, familyName, Borzage]
Generated description
Borzage is a surname most notably associated with Frank Borzage, an influential American film director and Academy Award winner of Hollywood’s early sound era.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Borzage Target entity description: Borzage is a surname most notably associated with Frank Borzage, an influential American film director and Academy Award winner of Hollywood’s early sound era.
-
A.
Modjeski
Modjeski is the surname of Ralph Modjeski, a prominent Polish-American civil engineer renowned for designing major bridges in the United States.
-
B.
Lorre
Lorre is a surname most notably associated with Hungarian-American actor Peter Lorre and his family.
-
C.
Bela Pratt
Bela Pratt was an American sculptor known for his public monuments and architectural sculptures, particularly in Boston and other U.S. cities.
-
D.
Mary Bogdanovich
Mary Bogdanovich is known as the spouse of American actor and film producer Brad Dexter.
-
E.
Lecy Goranson
Lecy Goranson is an American actress best known for playing Becky Conner on the sitcom "Roseanne" and its revival.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6590ed7988190bc6b610d1f4fa194 |
completed | April 20, 2026, 4:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07dbd5cb948190b1f2ce3d59114bce |
completed | May 16, 2026, 2:52 a.m. |
| NEDg | Description generation | batch_6a07dd2dd31c8190bf70aab957afbcf5 |
completed | May 16, 2026, 2:57 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07ddf82b8881908675230d8fbac101 |
completed | May 16, 2026, 3:01 a.m. |
Created at: April 10, 2026, 1:52 p.m.