Triple
T21527386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Calm with Horses |
E531130
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Cosmo Jarvis |
—
|
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: Cosmo Jarvis | Statement: [Calm with Horses, starring, Cosmo Jarvis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cosmo Jarvis Context triple: [Calm with Horses, starring, Cosmo Jarvis]
-
A.
Cosmo Jarvis
chosen
Cosmo Jarvis is a British-American singer-songwriter, actor, and filmmaker known for his genre-blending music and acclaimed performances in independent films and television dramas.
-
B.
Cosmo Brown
Cosmo Brown is the wisecracking, musically gifted best friend and sidekick to Don Lockwood in the classic Hollywood musical film "Singin' in the Rain."
-
C.
Jonathan Quarmby
Jonathan Quarmby is a British record producer and songwriter known for his work across diverse genres with artists ranging from indie and rock acts to mainstream pop performers.
-
D.
Jasper Woodcock
Jasper Woodcock is the tough, sarcastic gym teacher portrayed by Billy Bob Thornton in the 2007 comedy film "Mr. Woodcock."
-
E.
Martin Jarvis
Martin Jarvis is a British actor known for his extensive work in film, television, theatre, and as a prolific audiobook and radio drama narrator.
- 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_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee88522e948190b9fa5a3587f32eae |
completed | April 26, 2026, 9:49 p.m. |
Created at: April 16, 2026, 6:26 p.m.