Triple
T21176382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Punahou School |
E521822
|
entity |
| Predicate | notableAlumnus |
P304
|
FINISHED |
| Object | Steve Case |
—
|
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: Steve Case | Statement: [Punahou School, notableAlumnus, Steve Case]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Steve Case Context triple: [Punahou School, notableAlumnus, Steve Case]
-
A.
Steve Case
chosen
Steve Case is an American entrepreneur and investor best known as the co-founder and former CEO of AOL, a pioneering internet services company.
-
B.
Steve Levine
Steve Levine is a British record producer best known for his work in the 1980s with artists such as Culture Club and The Beach Boys.
-
C.
John Case
John Case is a relatively common personal name that may refer to multiple individuals across different fields, such as literature, academia, or public life.
-
D.
John Doerr
John Doerr is a prominent American venture capitalist and early investor in major technology companies such as Google and Amazon.
-
E.
Ray Ozzie
Ray Ozzie is an American software entrepreneur and technologist best known for creating Lotus Notes and later serving as a key strategic leader at Microsoft.
- 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_69e0b50ef1d48190b063aa342667df22 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e730197cfc8190bde13453b761886b |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 3 p.m.