Triple
T146444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zip2 |
E3340
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Greg Kouri
Greg Kouri was a Canadian entrepreneur and early investor best known for co-founding Zip2 alongside Elon and Kimbal Musk.
|
E21877
|
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: Greg Kouri | Statement: [Zip2, foundedBy, Greg Kouri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greg Kouri Context triple: [Zip2, foundedBy, Greg Kouri]
-
A.
Stephen E. Smith
Stephen E. Smith was an American businessman and political strategist closely associated with the Kennedy family, notably serving as a key adviser and organizer in their political campaigns.
-
B.
Jonathan Corwin
Jonathan Corwin was a 17th-century Massachusetts magistrate best known as one of the judges who presided over the Salem witch trials.
-
C.
Denis McDonough
Denis McDonough is an American political advisor who served as White House Chief of Staff under President Barack Obama.
-
D.
Ron Klain
Ron Klain is an American attorney, political consultant, and longtime Democratic operative who served as White House Chief of Staff under President Joe Biden.
-
E.
Alan M. Garber
Alan M. Garber is an American physician-economist and academic leader known for his work in health policy and for serving in top administrative roles at Harvard University.
- 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: Greg Kouri Triple: [Zip2, foundedBy, Greg Kouri]
Generated description
Greg Kouri was a Canadian entrepreneur and early investor best known for co-founding Zip2 alongside Elon and Kimbal Musk.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Greg Kouri Target entity description: Greg Kouri was a Canadian entrepreneur and early investor best known for co-founding Zip2 alongside Elon and Kimbal Musk.
-
A.
Stephen E. Smith
Stephen E. Smith was an American businessman and political strategist closely associated with the Kennedy family, notably serving as a key adviser and organizer in their political campaigns.
-
B.
Jonathan Corwin
Jonathan Corwin was a 17th-century Massachusetts magistrate best known as one of the judges who presided over the Salem witch trials.
-
C.
Denis McDonough
Denis McDonough is an American political advisor who served as White House Chief of Staff under President Barack Obama.
-
D.
Ron Klain
Ron Klain is an American attorney, political consultant, and longtime Democratic operative who served as White House Chief of Staff under President Joe Biden.
-
E.
Alan M. Garber
Alan M. Garber is an American physician-economist and academic leader known for his work in health policy and for serving in top administrative roles at Harvard University.
- 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_69a252868de4819080e21c9938bfe8b6 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a257eba6188190a3cf99c91bf3038f |
completed | Feb. 28, 2026, 2:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2eb788a888190bbb53e82559abbf3 |
completed | Feb. 28, 2026, 1:19 p.m. |
| NEDg | Description generation | batch_69a2ebe5644481908e221cc8724c99ae |
completed | Feb. 28, 2026, 1:21 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a2ec56b5208190a60feb32c732cebc |
completed | Feb. 28, 2026, 1:23 p.m. |
Created at: Feb. 28, 2026, 2:31 a.m.