Triple
T23486446
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bill Campbell |
E570545
|
entity |
| Predicate | mentorOf |
P7251
|
FINISHED |
| Object | Sergey Brin |
—
|
NE NERFINISHED |
How this triple was built (2 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: Sergey Brin | Statement: [Bill Campbell, mentorOf, Sergey Brin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sergey Brin Context triple: [Bill Campbell, mentorOf, Sergey Brin]
-
A.
Sergey Brin
chosen
Sergey Brin is a computer scientist and internet entrepreneur best known as the co-founder of Google.
-
B.
Larry Page
Larry Page is an American computer scientist and entrepreneur best known as the co-founder and former CEO of Google and its parent company Alphabet Inc.
-
C.
Sam Brin
Sam Brin is the brother of Google co-founder Sergey Brin and a member of the Brin family known for its ties to the tech industry.
-
D.
Urs Hölzle
Urs Hölzle is a Swiss computer scientist best known as one of Google’s first employees and its longtime Senior Vice President of Technical Infrastructure, where he has shaped the company’s large-scale computing systems.
-
E.
John Doerr
John Doerr is a prominent American venture capitalist and early investor in major technology companies such as Google and Amazon.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245b0b01481908f636939bedd804c |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a754825481909b005ca5654c3159 |
completed | April 29, 2026, 6:38 a.m. |
Created at: April 17, 2026, 6:04 p.m.