Triple
T1434040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vin Scully |
E30516
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Sandra Hunt
Sandra Hunt is best known as the wife of legendary Los Angeles Dodgers broadcaster Vin Scully.
|
E238103
|
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: Sandra Hunt | Statement: [Vin Scully, spouse, Sandra Hunt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandra Hunt Context triple: [Vin Scully, spouse, Sandra Hunt]
-
A.
Lynne Haldeman
Lynne Haldeman is a member of the Musk family and the sister of model and dietitian Maye Musk, making her an aunt of entrepreneur Elon Musk.
-
B.
Sandra Payne
Sandra Payne is a British actress known for her work in film and television, and for her former marriage to lyricist Alan Jay Lerner.
-
C.
Brenda Warner
Brenda Warner is an American philanthropist, former Marine, and motivational speaker best known as the wife of Hall of Fame NFL quarterback Kurt Warner and for her extensive charitable work and advocacy.
-
D.
Judith Nelson
Judith Nelson was an American soprano known for her pioneering work and acclaimed performances in the early music and Baroque repertoire.
-
E.
Adrienne Nesser
Adrienne Nesser is an American activist and former boutique owner best known as the longtime wife of Green Day frontman Billie Joe Armstrong.
- 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: Sandra Hunt Triple: [Vin Scully, spouse, Sandra Hunt]
Generated description
Sandra Hunt is best known as the wife of legendary Los Angeles Dodgers broadcaster Vin Scully.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sandra Hunt Target entity description: Sandra Hunt is best known as the wife of legendary Los Angeles Dodgers broadcaster Vin Scully.
-
A.
Lynne Haldeman
Lynne Haldeman is a member of the Musk family and the sister of model and dietitian Maye Musk, making her an aunt of entrepreneur Elon Musk.
-
B.
Sandra Payne
Sandra Payne is a British actress known for her work in film and television, and for her former marriage to lyricist Alan Jay Lerner.
-
C.
Brenda Warner
Brenda Warner is an American philanthropist, former Marine, and motivational speaker best known as the wife of Hall of Fame NFL quarterback Kurt Warner and for her extensive charitable work and advocacy.
-
D.
Judith Nelson
Judith Nelson was an American soprano known for her pioneering work and acclaimed performances in the early music and Baroque repertoire.
-
E.
Adrienne Nesser
Adrienne Nesser is an American activist and former boutique owner best known as the longtime wife of Green Day frontman Billie Joe Armstrong.
- 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_69a498fc69ec8190b61722bd4b67c4d2 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c4df1e3c819086646b709021d7f0 |
completed | March 1, 2026, 10:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae515ce1b0819089603a3e0f6b1933 |
completed | March 9, 2026, 4:49 a.m. |
| NEDg | Description generation | batch_69ae553d38f4819081d00f6c6451f7ed |
completed | March 9, 2026, 5:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae55875b5081909cfe62b222d229f6 |
completed | March 9, 2026, 5:07 a.m. |
Created at: March 1, 2026, 8 p.m.