Triple
T6082052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary McDonnell |
E135545
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Randle Mell
Randle Mell is an American actor known for his work in film, television, and theater, and for his long-term marriage to actress Mary McDonnell.
|
E566608
|
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: Randle Mell | Statement: [Mary McDonnell, spouse, Randle Mell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Randle Mell Context triple: [Mary McDonnell, spouse, Randle Mell]
-
A.
Maye
Maye is the first name of Maye Musk, a Canadian-South African model and dietitian known for her long-running fashion career and as the mother of entrepreneur Elon Musk.
-
B.
Darnell Nurse
Darnell Nurse is a Canadian professional ice hockey defenceman in the NHL, known for his physical play and leadership with the Edmonton Oilers.
-
C.
Cooke Maroney
Cooke Maroney is an American art gallery director known for his work in the contemporary art world and his marriage to actress Jennifer Lawrence.
-
D.
Rudy Baylor
Rudy Baylor is the idealistic young law school graduate who serves as the protagonist in John Grisham’s legal thriller "The Rainmaker."
-
E.
Jean Couzy
Jean Couzy was a French mountaineer best known as one of the climbers who achieved the first ascent of the Himalayan peak Makalu in 1955.
- 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: Randle Mell Triple: [Mary McDonnell, spouse, Randle Mell]
Generated description
Randle Mell is an American actor known for his work in film, television, and theater, and for his long-term marriage to actress Mary McDonnell.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Randle Mell Target entity description: Randle Mell is an American actor known for his work in film, television, and theater, and for his long-term marriage to actress Mary McDonnell.
-
A.
Maye
Maye is the first name of Maye Musk, a Canadian-South African model and dietitian known for her long-running fashion career and as the mother of entrepreneur Elon Musk.
-
B.
Darnell Nurse
Darnell Nurse is a Canadian professional ice hockey defenceman in the NHL, known for his physical play and leadership with the Edmonton Oilers.
-
C.
Cooke Maroney
Cooke Maroney is an American art gallery director known for his work in the contemporary art world and his marriage to actress Jennifer Lawrence.
-
D.
Rudy Baylor
Rudy Baylor is the idealistic young law school graduate who serves as the protagonist in John Grisham’s legal thriller "The Rainmaker."
-
E.
Jean Couzy
Jean Couzy was a French mountaineer best known as one of the climbers who achieved the first ascent of the Himalayan peak Makalu in 1955.
- 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_69c0087ad31c8190ab936e0ff28614b6 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05774bc948190a446b27e83f7079b |
completed | March 22, 2026, 8:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c11d57b5f481908d7df374837a486a |
completed | March 23, 2026, 11 a.m. |
| NEDg | Description generation | batch_69c11e89c75481908381df126a7b1661 |
completed | March 23, 2026, 11:05 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c11ef6971c8190b8dde5568b330b41 |
completed | March 23, 2026, 11:07 a.m. |
Created at: March 22, 2026, 4:11 p.m.