Triple
T21795658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sara Lee Corporation |
E538086
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Nathan Cummings
Nathan Cummings was a Canadian-American businessman and philanthropist best known for building the Sara Lee Corporation into a major global food conglomerate.
|
E1502953
|
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: Nathan Cummings | Statement: [Sara Lee Corporation, foundedBy, Nathan Cummings]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nathan Cummings Context triple: [Sara Lee Corporation, foundedBy, Nathan Cummings]
-
A.
John Cummings
John Cummings is a Scottish musician best known as a former guitarist of the post-rock band Mogwai.
-
B.
J. Morgan Cunningham
J. Morgan Cunningham is a pseudonym used by American crime and mystery novelist Donald E. Westlake.
-
C.
Cyrus G. Luce
Cyrus G. Luce was a 19th-century American politician who served as governor of Michigan and for whom Luce County in the state is named.
-
D.
Charles Noland
Charles Noland is an American actor known for his character roles in film, television, and theater.
-
E.
Daniel Wadsworth
Daniel Wadsworth was a prominent American art patron and philanthropist best known for founding the Wadsworth Atheneum, one of the first public art museums in the United States.
- 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: Nathan Cummings Triple: [Sara Lee Corporation, foundedBy, Nathan Cummings]
Generated description
Nathan Cummings was a Canadian-American businessman and philanthropist best known for building the Sara Lee Corporation into a major global food conglomerate.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Nathan Cummings Target entity description: Nathan Cummings was a Canadian-American businessman and philanthropist best known for building the Sara Lee Corporation into a major global food conglomerate.
-
A.
John Cummings
John Cummings is a Scottish musician best known as a former guitarist of the post-rock band Mogwai.
-
B.
J. Morgan Cunningham
J. Morgan Cunningham is a pseudonym used by American crime and mystery novelist Donald E. Westlake.
-
C.
Cyrus G. Luce
Cyrus G. Luce was a 19th-century American politician who served as governor of Michigan and for whom Luce County in the state is named.
-
D.
Charles Noland
Charles Noland is an American actor known for his character roles in film, television, and theater.
-
E.
Daniel Wadsworth
Daniel Wadsworth was a prominent American art patron and philanthropist best known for founding the Wadsworth Atheneum, one of the first public art museums in the United States.
- 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_69e0c4733f4081909a86622e7e6d15d2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f06223ecc48190bd3b173586ea7818 |
completed | April 28, 2026, 7:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a3e7e3b508190bccf7bfd6856861a |
completed | May 17, 2026, 10:17 p.m. |
| NEDg | Description generation | batch_6a0a4292891c8190a9d6202faa3eeb95 |
completed | May 17, 2026, 10:34 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a433f4528819099527393c5966cbb |
completed | May 17, 2026, 10:37 p.m. |
Created at: April 16, 2026, 6:53 p.m.