Triple
T18177866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loving |
E435208
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | Raindog Films |
—
|
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: Raindog Films | Statement: [Loving, productionCompany, Raindog Films]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Raindog Films Context triple: [Loving, productionCompany, Raindog Films]
-
A.
Raindog Films
chosen
Raindog Films is a British film production company co-founded by musician Peter Gabriel, known for producing socially conscious and politically themed films such as "Eye in the Sky."
-
B.
Black Dog Films
Black Dog Films is a production company and subsidiary of RSA Films known for creating innovative music videos, commercials, and short-form visual content.
-
C.
Mad Dog Films
Mad Dog Films is a television production company best known for producing the sketch comedy series MADtv.
-
D.
Big Dog Films
Big Dog Films is a film production company best known for producing the 1998 crime drama film "Belly."
-
E.
Kandoo Films
Kandoo Films is a film and television production company known for backing socially conscious and critically acclaimed projects such as the documentary "13th."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b90c7ec081909b4694ccecb449c6 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4df5b68f081908aac8210270f1499 |
completed | April 19, 2026, 1:57 p.m. |
Created at: April 10, 2026, 10:31 a.m.