Triple
T22566317
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ADP |
E557960
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Henry Taub |
—
|
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: Henry Taub | Statement: [ADP, foundedBy, Henry Taub]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henry Taub Context triple: [ADP, foundedBy, Henry Taub]
-
A.
Henry Taub
chosen
Henry Taub was an American businessman and philanthropist best known as a co-founder of the payroll and human resources company Automatic Data Processing (ADP).
-
B.
Jonathan Toubin
Jonathan Toubin is an American DJ, music promoter, and former musician best known for his influential New York Night Train soul and rock ’n’ roll dance parties.
-
C.
Henry Krinsky
Henry Krinsky, later known as Henry Crown, was a prominent American industrialist and financier who built a vast business empire including Material Service Corporation and a major stake in General Dynamics.
-
D.
Larry Hochman
Larry Hochman is an American orchestrator and composer best known for his work on numerous Broadway productions and his Tony Award–winning orchestrations.
-
E.
Carl Shulman
Carl Shulman is a researcher and thinker known for his work on existential risk, AI alignment, and long-term future strategy, particularly through his role at Oxford’s Future of Humanity Institute.
- 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_69e11e5ae4ac8190b1f503457603d969 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15faaa0b081908d5aa8f3ba1e3dd3 |
completed | April 29, 2026, 1:32 a.m. |
Created at: April 16, 2026, 8:52 p.m.