Triple
T3200694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sandra Lee |
E67041
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Bruce Karatz
Bruce Karatz is an American businessman best known as the former chairman and CEO of homebuilding company KB Home.
|
E336483
|
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: Bruce Karatz | Statement: [Sandra Lee, spouse, Bruce Karatz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bruce Karatz Context triple: [Sandra Lee, spouse, Bruce Karatz]
-
A.
Brian Marts
Brian Marts is an American mountaineer known for being among the first climbers to successfully ascend Vinson Massif, the highest peak in Antarctica.
-
B.
John Kamps
John Kamps is an American screenwriter best known for co-writing the family science fiction film "Zathura: A Space Adventure."
-
C.
Michael Kuzak
Michael Kuzak is a central attorney character on the television legal drama "L.A. Law," known for his idealism and high-profile courtroom battles.
-
D.
Mike Krieger
Mike Krieger is a Brazilian-American entrepreneur and software engineer best known as the co-founder and former CTO of the photo-sharing social media platform Instagram.
-
E.
Keith Kaseman
Keith Kaseman is an American architect best known as the co-designer of the National 9/11 Pentagon Memorial in Arlington, Virginia.
- 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: Bruce Karatz Triple: [Sandra Lee, spouse, Bruce Karatz]
Generated description
Bruce Karatz is an American businessman best known as the former chairman and CEO of homebuilding company KB Home.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bruce Karatz Target entity description: Bruce Karatz is an American businessman best known as the former chairman and CEO of homebuilding company KB Home.
-
A.
Brian Marts
Brian Marts is an American mountaineer known for being among the first climbers to successfully ascend Vinson Massif, the highest peak in Antarctica.
-
B.
John Kamps
John Kamps is an American screenwriter best known for co-writing the family science fiction film "Zathura: A Space Adventure."
-
C.
Michael Kuzak
Michael Kuzak is a central attorney character on the television legal drama "L.A. Law," known for his idealism and high-profile courtroom battles.
-
D.
Mike Krieger
Mike Krieger is a Brazilian-American entrepreneur and software engineer best known as the co-founder and former CTO of the photo-sharing social media platform Instagram.
-
E.
Keith Kaseman
Keith Kaseman is an American architect best known as the co-designer of the National 9/11 Pentagon Memorial in Arlington, Virginia.
- 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_69ad8589bd988190afa7ed2bdffb7b33 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada9aedef08190824bdf508f85f06f |
completed | March 8, 2026, 4:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b24bc3695c8190abd58dbc74ca2271 |
completed | March 12, 2026, 5:14 a.m. |
| NEDg | Description generation | batch_69b24d677ca8819094cb03360ac885da |
completed | March 12, 2026, 5:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b2517e2afc8190a6f8dfa66d3671d5 |
completed | March 12, 2026, 5:39 a.m. |
Created at: March 8, 2026, 3:07 p.m.