Triple
T30046290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Howard Barish |
E763461
|
entity |
| Predicate | companyTypeOfKandooFilms |
P39595
|
FINISHED |
| Object | production company |
—
|
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: production company | Statement: [Howard Barish, companyTypeOfKandooFilms, production company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: companyTypeOfKandooFilms Context triple: [Howard Barish, companyTypeOfKandooFilms, production company]
-
A.
KandooFilmsFocus
Indicates that Kandoo Films centers its work, attention, or primary activities on a particular subject, project, or area.
-
B.
coProductionCompany
Indicates a company that collaborates with one or more other companies in the joint production of a work or project.
-
C.
productionCompanyType
chosen
Indicates the specific category or kind of production company associated with a given entity.
-
D.
productionCompanyOfWork
Indicates that a company is responsible for producing a particular creative work (such as a film, TV show, or similar production).
-
E.
ownedProductionCompany
Indicates that one entity previously possessed ownership or controlling interest in a production company.
- 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_69f22470a89c8190be7273297c0e0d19 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f74c70fd248190a9d5543afcb08211 |
completed | May 3, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69f7478e3b548190a51d5d436e2bb036 |
completed | May 3, 2026, 1:03 p.m. |
Created at: April 29, 2026, 6:54 p.m.