Triple
T3780514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greylock Partners |
E85404
|
entity |
| Predicate | founder |
P104
|
FINISHED |
| Object |
Dan Gregory
Dan Gregory is a venture capitalist best known as a co-founder of the prominent Silicon Valley investment firm Greylock Partners.
|
E387787
|
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: Dan Gregory | Statement: [Greylock Partners, founder, Dan Gregory]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dan Gregory Context triple: [Greylock Partners, founder, Dan Gregory]
-
A.
Dan Gordon
Dan Gordon is an American screenwriter known for his work on films such as "The Hurricane" and "Wyatt Earp."
-
B.
Don Brautigam
Don Brautigam was an American illustrator best known for his striking, realistic cover art for horror and thriller novels, including works by Stephen King.
-
C.
Brad Van Pelt
Brad Van Pelt was a standout linebacker for the New York Giants in the 1970s and early 1980s, known for his Pro Bowl-caliber play and leadership on defense.
-
D.
Bill Nunn
Bill Nunn was an American character actor best known for his memorable supporting roles in films like "Do the Right Thing" and the "Spider-Man" trilogy.
-
E.
Alan Osbiston
Alan Osbiston was a British film editor known for his work on notable mid-20th-century films, including major war and drama productions.
- 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: Dan Gregory Triple: [Greylock Partners, founder, Dan Gregory]
Generated description
Dan Gregory is a venture capitalist best known as a co-founder of the prominent Silicon Valley investment firm Greylock Partners.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dan Gregory Target entity description: Dan Gregory is a venture capitalist best known as a co-founder of the prominent Silicon Valley investment firm Greylock Partners.
-
A.
Dan Gordon
Dan Gordon is an American screenwriter known for his work on films such as "The Hurricane" and "Wyatt Earp."
-
B.
Don Brautigam
Don Brautigam was an American illustrator best known for his striking, realistic cover art for horror and thriller novels, including works by Stephen King.
-
C.
Brad Van Pelt
Brad Van Pelt was a standout linebacker for the New York Giants in the 1970s and early 1980s, known for his Pro Bowl-caliber play and leadership on defense.
-
D.
Bill Nunn
Bill Nunn was an American character actor best known for his memorable supporting roles in films like "Do the Right Thing" and the "Spider-Man" trilogy.
-
E.
Alan Osbiston
Alan Osbiston was a British film editor known for his work on notable mid-20th-century films, including major war and drama productions.
- 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_69aed937fa8881908208ef3801060826 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee3d84d7881909828903896b3cb7f |
completed | March 9, 2026, 3:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4f040676c8190aa3a7952a9d6f62b |
completed | March 14, 2026, 5:21 a.m. |
| NEDg | Description generation | batch_69b4f159d7e88190a76d51378ba141d3 |
completed | March 14, 2026, 5:25 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4f220f9388190b2c3615f713f01f2 |
completed | March 14, 2026, 5:29 a.m. |
Created at: March 9, 2026, 3:12 p.m.