Triple
T22944528
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick Collison |
E569828
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | John Collison |
—
|
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: John Collison | Statement: [Patrick Collison, sibling, John Collison]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Collison Context triple: [Patrick Collison, sibling, John Collison]
-
A.
John Collison
chosen
John Collison is an Irish entrepreneur best known as the co-founder and president of the online payments company Stripe.
-
B.
Robb Armstrong
Robb Armstrong is an American cartoonist best known as the creator of the long-running syndicated comic strip "JumpStart."
-
C.
Brian Armstrong
Brian Armstrong is an American entrepreneur best known as the co-founder and CEO of the cryptocurrency exchange Coinbase.
-
D.
Peter Thiel
Peter Thiel is a German-American entrepreneur, venture capitalist, and political activist best known as a co-founder of PayPal and an early investor in Facebook.
-
E.
Keith Rabois
Keith Rabois is an American technology executive, entrepreneur, and venture capitalist known for early leadership roles at companies like PayPal, LinkedIn, and Square and for his investments in numerous successful startups.
- 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_69e2459199d08190a8184ee2aa935842 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1819c696c8190977bd2bca01509bc |
completed | April 29, 2026, 3:57 a.m. |
Created at: April 17, 2026, 3:45 p.m.