Triple
T10557785
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mike Medavoy |
E249133
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Phoenix Pictures |
E244199
|
NE 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: Phoenix Pictures | Statement: [Mike Medavoy, employer, Phoenix Pictures]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Phoenix Pictures Context triple: [Mike Medavoy, employer, Phoenix Pictures]
-
A.
Phoenix Pictures
chosen
Phoenix Pictures is an American film production company known for producing critically acclaimed movies such as "Black Swan" and "The Thin Red Line."
-
B.
Sun Pictures
Sun Pictures is a prominent Indian film production and distribution company best known for producing major Tamil-language blockbuster movies.
-
C.
Lewis Pictures
Lewis Pictures is a South Korean film production company known for backing acclaimed works such as Bong Joon-ho’s fantasy drama "Okja."
-
D.
Park Pictures
Park Pictures is a production company known for its acclaimed work in commercials, music videos, and feature films.
-
E.
Polygon Pictures
Polygon Pictures is a Japanese animation studio known for its 3D CGI work on numerous anime series and international co-productions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d381c733c08190ab1dd6239f5f34ae |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5271521a4819086d96e1f183ab07a |
completed | April 7, 2026, 3:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9347ae67081909cb2c3911cb1be67 |
completed | April 10, 2026, 5:33 p.m. |
Created at: April 6, 2026, 12:35 p.m.