Triple
T5226172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sophie Tucker |
E117991
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Louis Tuck
Louis Tuck was the husband of famed American singer and comedian Sophie Tucker.
|
E503899
|
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: Louis Tuck | Statement: [Sophie Tucker, spouse, Louis Tuck]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Louis Tuck Context triple: [Sophie Tucker, spouse, Louis Tuck]
-
A.
Eugene Tennant
Eugene Tennant is the father of British actress Victoria Tennant.
-
B.
Louis Hobson
Louis Hobson is an American musical theatre actor best known for his work on Broadway, including originating a role in the acclaimed rock musical "Next to Normal."
-
C.
George Crocker
George Crocker was an American financier and railroad executive, known as the son and heir of railroad magnate Charles Crocker and for his significant philanthropic activities.
-
D.
Louis Tully
Louis Tully is a nerdy, well-meaning accountant and neighbor of Dana Barrett who becomes a comedic, possessed pawn of Gozer in the Ghostbusters films.
-
E.
Cecil Hartnett
Cecil Hartnett is an individual notable enough to be recognized as a bearer of the Hartnett surname, though specific public details about his life or achievements are not widely documented.
- 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: Louis Tuck Triple: [Sophie Tucker, spouse, Louis Tuck]
Generated description
Louis Tuck was the husband of famed American singer and comedian Sophie Tucker.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Louis Tuck Target entity description: Louis Tuck was the husband of famed American singer and comedian Sophie Tucker.
-
A.
Eugene Tennant
Eugene Tennant is the father of British actress Victoria Tennant.
-
B.
Louis Hobson
Louis Hobson is an American musical theatre actor best known for his work on Broadway, including originating a role in the acclaimed rock musical "Next to Normal."
-
C.
George Crocker
George Crocker was an American financier and railroad executive, known as the son and heir of railroad magnate Charles Crocker and for his significant philanthropic activities.
-
D.
Louis Tully
Louis Tully is a nerdy, well-meaning accountant and neighbor of Dana Barrett who becomes a comedic, possessed pawn of Gozer in the Ghostbusters films.
-
E.
Cecil Hartnett
Cecil Hartnett is an individual notable enough to be recognized as a bearer of the Hartnett surname, though specific public details about his life or achievements are not widely documented.
- 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_69bd4466fb8c819083b806a79414d7e4 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7adc9be081909903b9f844c3d146 |
completed | March 20, 2026, 4:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69beeffc51888190938dc157b14c4b6c |
completed | March 21, 2026, 7:22 p.m. |
| NEDg | Description generation | batch_69bef0b2b6448190be1c465738be741b |
completed | March 21, 2026, 7:25 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bef121817c8190aebd27ee34c0a419 |
completed | March 21, 2026, 7:27 p.m. |
Created at: March 20, 2026, 1:48 p.m.