Triple
T21869569
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Decision to Leave |
E539966
|
entity |
| Predicate | distributor |
P1951
|
FINISHED |
| Object |
MUBI
MUBI is a curated global streaming platform and film distributor known for showcasing arthouse, independent, and international cinema.
|
E1506565
|
NE FINISHED |
How this triple was built (4 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: MUBI | Statement: [Decision to Leave, distributor, MUBI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MUBI Context triple: [Decision to Leave, distributor, MUBI]
-
A.
Mubi
Mubi is an Afroasiatic Chadic language spoken primarily in parts of Chad.
-
B.
Mubi
Mubi is a town in Adamawa State, northeastern Nigeria, known as a commercial hub near the Cameroon border and as the site of several deadly insurgent attacks.
-
C.
FilmStruck
FilmStruck was a subscription-based streaming service specializing in classic, arthouse, and independent films, including titles from the Criterion Collection.
-
D.
BFI Player
BFI Player is the British Film Institute’s online streaming service offering a curated selection of classic, independent, and archive films.
-
E.
Movies on Demand
Movies on Demand is a film or video project associated with the band Consequence, likely serving as a notable visual or multimedia extension of their music.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: MUBI Triple: [Decision to Leave, distributor, MUBI]
Generated description
MUBI is a curated global streaming platform and film distributor known for showcasing arthouse, independent, and international cinema.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MUBI Target entity description: MUBI is a curated global streaming platform and film distributor known for showcasing arthouse, independent, and international cinema.
-
A.
Mubi
Mubi is an Afroasiatic Chadic language spoken primarily in parts of Chad.
-
B.
Mubi
Mubi is a town in Adamawa State, northeastern Nigeria, known as a commercial hub near the Cameroon border and as the site of several deadly insurgent attacks.
-
C.
FilmStruck
FilmStruck was a subscription-based streaming service specializing in classic, arthouse, and independent films, including titles from the Criterion Collection.
-
D.
BFI Player
BFI Player is the British Film Institute’s online streaming service offering a curated selection of classic, independent, and archive films.
-
E.
Movies on Demand
Movies on Demand is a film or video project associated with the band Consequence, likely serving as a notable visual or multimedia extension of their music.
- F. None of above. chosen
Provenance (5 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_69e0c478f59081909d54302b57fc1ce3 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0f334362c819094af465ee57b47e6 |
completed | April 28, 2026, 5:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a529bf45c8190a3772a70549dff43 |
completed | May 17, 2026, 11:43 p.m. |
| NEDg | Description generation | batch_6a0a5461f3d481908637fb7aaceb128b |
completed | May 17, 2026, 11:50 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a54dfee308190827568d6a2ba5675 |
completed | May 17, 2026, 11:53 p.m. |
Created at: April 16, 2026, 6:57 p.m.