Triple
T11964759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Archibald Selwyn |
E284762
|
entity |
| Predicate | coFoundedCompanyType |
P5179
|
FINISHED |
| Object | film studio |
—
|
LITERAL FINISHED |
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: film studio | Statement: [Archibald Selwyn, coFoundedCompanyType, film studio]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coFoundedCompanyType Context triple: [Archibald Selwyn, coFoundedCompanyType, film studio]
-
A.
coFounderCompany
Indicates that a person is one of the founding members who jointly established a particular company.
-
B.
foundedCompany
Indicates that an entity established or created a company, typically as its founder or co-founder.
-
C.
foundedOrganizationType
chosen
Indicates that an entity established or created an organization of a specified type (e.g., company, nonprofit, institution).
-
D.
companyFoundedWith
Indicates that a company was established using or in association with a particular resource, organization, or founding context.
-
E.
backedCompanyType
Indicates the type or category of company that is being financially supported or invested in by another party.
- 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_69d6ab2eaeb881909f7914758f859413 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903799f948190a5dc4d3822f3ff27 |
completed | April 10, 2026, 2:04 p.m. |
| PD | Predicate disambiguation | batch_69d8bb40f30c8190a0e0719bd67542bf |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:45 p.m.