Triple
T1005645
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cole Porter |
E21703
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Linda Lee Thomas
Linda Lee Thomas was an American socialite and wealthy heiress best known as the elegant and influential wife and muse of composer Cole Porter.
|
E175404
|
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: Linda Lee Thomas | Statement: [Cole Porter, spouse, Linda Lee Thomas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Linda Lee Thomas Context triple: [Cole Porter, spouse, Linda Lee Thomas]
-
A.
Janet Norton Lee
Janet Norton Lee was an American socialite and philanthropist best known as the mother of First Lady Jacqueline Kennedy Onassis.
-
B.
Mary Lee Woods
Mary Lee Woods was a British mathematician and computer scientist who worked on early computers at Ferranti and was the mother of World Wide Web inventor Tim Berners-Lee.
-
C.
Mary McBride Smith
Mary McBride Smith was the wife of renowned American film director John Ford.
-
D.
Florence Lee
Florence Lee was an early 20th-century film actress best known for her supporting roles in silent comedies, including work with Charlie Chaplin.
-
E.
Valerie June Bowman
Valerie June Bowman, better known as Valerie Jarrett, is an American lawyer, businesswoman, and former senior advisor to President Barack Obama.
- 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: Linda Lee Thomas Triple: [Cole Porter, spouse, Linda Lee Thomas]
Generated description
Linda Lee Thomas was an American socialite and wealthy heiress best known as the elegant and influential wife and muse of composer Cole Porter.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Linda Lee Thomas Target entity description: Linda Lee Thomas was an American socialite and wealthy heiress best known as the elegant and influential wife and muse of composer Cole Porter.
-
A.
Janet Norton Lee
Janet Norton Lee was an American socialite and philanthropist best known as the mother of First Lady Jacqueline Kennedy Onassis.
-
B.
Mary Lee Woods
Mary Lee Woods was a British mathematician and computer scientist who worked on early computers at Ferranti and was the mother of World Wide Web inventor Tim Berners-Lee.
-
C.
Mary McBride Smith
Mary McBride Smith was the wife of renowned American film director John Ford.
-
D.
Florence Lee
Florence Lee was an early 20th-century film actress best known for her supporting roles in silent comedies, including work with Charlie Chaplin.
-
E.
Valerie June Bowman
Valerie June Bowman, better known as Valerie Jarrett, is an American lawyer, businesswoman, and former senior advisor to President Barack Obama.
- 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_69a493c53e648190ae8cb76c433fd9a7 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b51303548190a5ee3c0797fc3245 |
completed | March 1, 2026, 9:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad307c46988190bb4ba823ad313a88 |
completed | March 8, 2026, 8:17 a.m. |
| NEDg | Description generation | batch_69ad312e77ac8190b931a42317f2cefa |
completed | March 8, 2026, 8:19 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ad3184853c8190953b288693ce6ea4 |
completed | March 8, 2026, 8:21 a.m. |
Created at: March 1, 2026, 7:41 p.m.