Triple
T26406101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morton, Bliss & Co. |
E663836
|
entity |
| Predicate | coFounderLaterOffice |
P160510
|
FINISHED |
| Object | Levi P. Morton – Governor of New York |
—
|
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: Levi P. Morton – Governor of New York | Statement: [Morton, Bliss & Co., coFounderLaterOffice, Levi P. Morton – Governor of New York]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coFounderLaterOffice Context triple: [Morton, Bliss & Co., coFounderLaterOffice, Levi P. Morton – Governor of New York]
-
A.
coFounderLaterPosition
chosen
Indicates that an individual who co-founded an organization later held a specific position or role within that same organization.
-
B.
coFounderCompany
Indicates that a person is one of the founding members who jointly established a particular company.
-
C.
coFounderWith
Indicates that two or more entities jointly founded the same organization or venture.
-
D.
coFounderOfFounder
Indicates that one entity is a co-founder of another entity who is themselves a founder of something else.
-
E.
hasCoFounderRoleOf
Indicates that one entity holds the role or position of co-founder in relation to another entity, such as an organization or venture.
- 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_69ee883931888190901be96d75ee23cc |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f610f87374819084279ca5c2f3d32f |
completed | May 2, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69f602d2ec748190ae95154f34c7878f |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 26, 2026, 11:35 p.m.