Triple
T33694736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pullman family |
E863271
|
entity |
| Predicate | hasFounderOfAssociatedCompany |
P143912
|
FINISHED |
| Object | George Pullman |
—
|
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: George Pullman | Statement: [Pullman family, hasFounderOfAssociatedCompany, George Pullman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFounderOfAssociatedCompany Context triple: [Pullman family, hasFounderOfAssociatedCompany, George Pullman]
-
A.
hasParentCompanyFounder
Indicates that an entity is the founder of the parent company of another entity.
-
B.
hasFounderRelationship
Indicates a relationship where one entity serves as the founder or co-founder of another entity.
-
C.
companyFounderAssociated
chosen
Indicates that there is a notable connection or involvement between a company and an individual recognized as its founder.
-
D.
hasFounderPreviousAffiliation
Indicates that a founder of an entity was previously affiliated (e.g., employed, enrolled, or otherwise formally associated) with another organization or institution.
-
E.
hasFormerFounder
Indicates that an entity was previously a founder of another entity but no longer holds that founder role or status.
- 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_69f3498723a08190ac034339cc78eade |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fdb04ed81c8190b8feea90c1c785a6 |
completed | May 8, 2026, 9:43 a.m. |
| PD | Predicate disambiguation | batch_69fda9d6c5148190a63205b6d9b0a1b4 |
completed | May 8, 2026, 9:16 a.m. |
Created at: May 1, 2026, 1:43 a.m.