Triple
T20609938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Shelter (2015 film) |
E506419
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object |
Bruise Productions
Bruise Productions is a film production company known for producing the 2015 drama film "The Shelter."
|
E1439736
|
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: Bruise Productions | Statement: [The Shelter (2015 film), productionCompany, Bruise Productions]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bruise Productions Context triple: [The Shelter (2015 film), productionCompany, Bruise Productions]
-
A.
Brut Productions
Brut Productions was a film production company active in the 1970s, known for backing a range of offbeat and genre films.
-
B.
Indelible Productions
Indelible Productions is a film production company best known for its work on the thriller movie "Panic Room."
-
C.
Albert Productions
Albert Productions is an Australian independent record label and production company best known for discovering and nurturing rock bands such as AC/DC.
-
D.
Black & White Productions
Black & White Productions is a film production company known for producing the comedy movie "Nacho Libre."
-
E.
Ardent Productions
Ardent Productions is a British television and film production company founded and run by Prince Edward, Earl of Wessex.
- 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: Bruise Productions Triple: [The Shelter (2015 film), productionCompany, Bruise Productions]
Generated description
Bruise Productions is a film production company known for producing the 2015 drama film "The Shelter."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bruise Productions Target entity description: Bruise Productions is a film production company known for producing the 2015 drama film "The Shelter."
-
A.
Brut Productions
Brut Productions was a film production company active in the 1970s, known for backing a range of offbeat and genre films.
-
B.
Indelible Productions
Indelible Productions is a film production company best known for its work on the thriller movie "Panic Room."
-
C.
Albert Productions
Albert Productions is an Australian independent record label and production company best known for discovering and nurturing rock bands such as AC/DC.
-
D.
Black & White Productions
Black & White Productions is a film production company known for producing the comedy movie "Nacho Libre."
-
E.
Ardent Productions
Ardent Productions is a British television and film production company founded and run by Prince Edward, Earl of Wessex.
- 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_69e0b4bb2b4081908fa4a72444120f35 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aad5e53c8190b0add34ce9b31d57 |
completed | April 20, 2026, 10:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08b3f98e5c8190833d0e47b3e9585b |
completed | May 16, 2026, 6:14 p.m. |
| NEDg | Description generation | batch_6a08b5a15a7c819099923f5a4d5f92c0 |
completed | May 16, 2026, 6:21 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08b603cd8481908780f4670dabf4a0 |
completed | May 16, 2026, 6:23 p.m. |
Created at: April 16, 2026, 11:41 a.m.