Triple
T15731234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paranormal Activity 3 |
E381348
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object |
Solana Films
Solana Films is a film production company best known for its work on the horror franchise entry "Paranormal Activity 3."
|
E1173773
|
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: Solana Films | Statement: [Paranormal Activity 3, productionCompany, Solana Films]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Solana Films Context triple: [Paranormal Activity 3, productionCompany, Solana Films]
-
A.
Cinelou Films
Cinelou Films is an independent American film production company known for producing character-driven dramas such as the 2014 film "Cake."
-
B.
Ventana Films
Ventana Films is a film production company known for its work on Guillermo del Toro’s acclaimed 1993 horror-fantasy film "Cronos."
-
C.
Scion Films
Scion Films is a British film production company known for backing acclaimed dramas such as "The Constant Gardener."
-
D.
Sunrise Films
Sunrise Films is a film distribution company known for handling the release of independent and international movies such as "Dinner Rush."
-
E.
Vinson Films
Vinson Films is a film production company known for producing the 2019 horror-comedy thriller "Ready or Not."
- 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: Solana Films Triple: [Paranormal Activity 3, productionCompany, Solana Films]
Generated description
Solana Films is a film production company best known for its work on the horror franchise entry "Paranormal Activity 3."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Solana Films Target entity description: Solana Films is a film production company best known for its work on the horror franchise entry "Paranormal Activity 3."
-
A.
Cinelou Films
Cinelou Films is an independent American film production company known for producing character-driven dramas such as the 2014 film "Cake."
-
B.
Ventana Films
Ventana Films is a film production company known for its work on Guillermo del Toro’s acclaimed 1993 horror-fantasy film "Cronos."
-
C.
Scion Films
Scion Films is a British film production company known for backing acclaimed dramas such as "The Constant Gardener."
-
D.
Sunrise Films
Sunrise Films is a film distribution company known for handling the release of independent and international movies such as "Dinner Rush."
-
E.
Vinson Films
Vinson Films is a film production company known for producing the 2019 horror-comedy thriller "Ready or Not."
- 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_69d86d9cdb648190bf3171be0bd7d872 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04fb61cb881908b158609c1ccfa1e |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff82fcb4e4819097bd0591bbcc3b71 |
completed | May 9, 2026, 6:54 p.m. |
| NEDg | Description generation | batch_69ff83ca33d08190816130bf2ea735df |
completed | May 9, 2026, 6:58 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff8469354c819080b8cfddb7c66be5 |
completed | May 9, 2026, 7 p.m. |
Created at: April 10, 2026, 4:46 a.m.