Triple
T23186609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | REGN |
E579608
|
entity |
| Predicate | hasUnderlyingCompanyCoFounder |
P87173
|
FINISHED |
| Object | Leonard S. Schleifer |
—
|
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: Leonard S. Schleifer | Statement: [REGN, hasUnderlyingCompanyCoFounder, Leonard S. Schleifer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUnderlyingCompanyCoFounder Context triple: [REGN, hasUnderlyingCompanyCoFounder, Leonard S. Schleifer]
-
A.
hasCoFounderRoleOf
Indicates that one entity holds the role or position of co-founder in relation to another entity, such as an organization or venture.
-
B.
hasParentCompanyFounder
Indicates that an entity is the founder of the parent company of another entity.
-
C.
hasUnderlyingCompanyCEO
Indicates that a specified company has a particular person serving as its Chief Executive Officer (CEO) at a fundamental or primary organizational level.
-
D.
hasCoFounderRole
chosen
Indicates that an entity holds or is assigned the role of co-founder in relation to another entity (such as an organization or project).
-
E.
founderAlsoOwns
Indicates that the person or entity who founded something also retains ownership of it.
- F. None of above.
Provenance (3 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_69e245ff8000819090d12008805315b7 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18fd3aaa08190b9cf7afe4ee5a38d |
completed | April 29, 2026, 4:57 a.m. |
| PD | Predicate disambiguation | batch_69ef8a041c0081909afb670d17a5aaba |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:05 p.m.