Triple
T22767618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Legacy of Rage |
E563169
|
entity |
| Predicate | distributedBy |
P1951
|
FINISHED |
| Object |
D&B Films
D&B Films was a Hong Kong-based film production and distribution company active mainly in the 1980s and 1990s, known for its action and crime movies.
|
E1553445
|
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: D&B Films | Statement: [Legacy of Rage, distributedBy, D&B Films]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: D&B Films Context triple: [Legacy of Rage, distributedBy, D&B Films]
-
A.
Decibel Films
Decibel Films is a film production company known for producing the 2018 thriller "Yesterday."
-
B.
Decibel Films
Decibel Films is a British film production company associated with producer Christian Colson, known for developing and producing feature films.
-
C.
Beyond Films
Beyond Films is an Australian film distribution and production company known for handling a range of independent and international titles.
-
D.
Darius Films
Darius Films is a Canadian independent film and television production company known for producing a range of genre-spanning features and series.
-
E.
Brio Films
Brio Films is a French film production company known for producing imaginative and visually distinctive movies such as Michel Gondry’s "Mood Indigo."
- 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: D&B Films Triple: [Legacy of Rage, distributedBy, D&B Films]
Generated description
D&B Films was a Hong Kong-based film production and distribution company active mainly in the 1980s and 1990s, known for its action and crime movies.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: D&B Films Target entity description: D&B Films was a Hong Kong-based film production and distribution company active mainly in the 1980s and 1990s, known for its action and crime movies.
-
A.
Decibel Films
Decibel Films is a film production company known for producing the 2018 thriller "Yesterday."
-
B.
Decibel Films
Decibel Films is a British film production company associated with producer Christian Colson, known for developing and producing feature films.
-
C.
Beyond Films
Beyond Films is an Australian film distribution and production company known for handling a range of independent and international titles.
-
D.
Darius Films
Darius Films is a Canadian independent film and television production company known for producing a range of genre-spanning features and series.
-
E.
Brio Films
Brio Films is a French film production company known for producing imaginative and visually distinctive movies such as Michel Gondry’s "Mood Indigo."
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17a81d3348190b005a43a5e03d406 |
completed | April 29, 2026, 3:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b981f3a1c819083a7d498290af751 |
completed | May 18, 2026, 10:52 p.m. |
| NEDg | Description generation | batch_6a0b98d159688190a5ec037ee8692f33 |
completed | May 18, 2026, 10:55 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b99b6e7e88190995319351374f97c |
completed | May 18, 2026, 10:59 p.m. |
Created at: April 17, 2026, 3:27 p.m.