Triple
T1503525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OpenDNS |
E33848
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
David Ulevitch
David Ulevitch is an American technology entrepreneur and investor best known as the founder of the DNS and internet security company OpenDNS.
|
E217952
|
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: David Ulevitch | Statement: [OpenDNS, foundedBy, David Ulevitch]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Ulevitch Context triple: [OpenDNS, foundedBy, David Ulevitch]
-
A.
Chris Lebenzon
Chris Lebenzon is an American film editor known for his long-time collaborations with directors like Tim Burton and Tony Scott on major Hollywood films.
-
B.
Phil Szostak
Phil Szostak is an American architect best known for designing the Durham Performing Arts Center in North Carolina.
-
C.
Jay O. Rothman
Jay O. Rothman is an American attorney and academic leader who serves as president of the University of Wisconsin System.
-
D.
Michael P. Brenner
Michael P. Brenner is an American applied mathematician and physicist known for his influential work in fluid dynamics and complex systems.
-
E.
Sam Zussman
Sam Zussman is a sports and media executive who serves as a top business leader for the NBA’s Brooklyn Nets organization.
- 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: David Ulevitch Triple: [OpenDNS, foundedBy, David Ulevitch]
Generated description
David Ulevitch is an American technology entrepreneur and investor best known as the founder of the DNS and internet security company OpenDNS.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: David Ulevitch Target entity description: David Ulevitch is an American technology entrepreneur and investor best known as the founder of the DNS and internet security company OpenDNS.
-
A.
Chris Lebenzon
Chris Lebenzon is an American film editor known for his long-time collaborations with directors like Tim Burton and Tony Scott on major Hollywood films.
-
B.
Phil Szostak
Phil Szostak is an American architect best known for designing the Durham Performing Arts Center in North Carolina.
-
C.
Jay O. Rothman
Jay O. Rothman is an American attorney and academic leader who serves as president of the University of Wisconsin System.
-
D.
Michael P. Brenner
Michael P. Brenner is an American applied mathematician and physicist known for his influential work in fluid dynamics and complex systems.
-
E.
Sam Zussman
Sam Zussman is a sports and media executive who serves as a top business leader for the NBA’s Brooklyn Nets organization.
- 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_69a885f352a4819099b24ff15489dede |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a8872fae4c81908e7d6961e6c5fa96 |
completed | March 4, 2026, 7:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adfb8d636c8190a8a9ca29d8a6fd82 |
completed | March 8, 2026, 10:43 p.m. |
| NEDg | Description generation | batch_69adfc9a4060819085d69a8642e49673 |
completed | March 8, 2026, 10:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69adfd03414c8190b1fc2b5608563726 |
completed | March 8, 2026, 10:49 p.m. |
Created at: March 4, 2026, 7:24 p.m.