Triple
T20103909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Breach |
E496617
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object |
MPG Films
MPG Films is a film production company known for producing the 2007 legal thriller "Breach."
|
E1412165
|
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: MPG Films | Statement: [Breach, productionCompany, MPG Films]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MPG Films Context triple: [Breach, productionCompany, MPG Films]
-
A.
M6 Films
M6 Films is a French film production company known for backing popular international action and thriller movies.
-
B.
MPM Film
MPM Film is a film production company known for developing and producing independent and international cinema projects.
-
C.
Lippert Films
Lippert Films was an American independent film distribution and production company active in the mid-20th century, known for handling low-budget genre movies.
-
D.
Maverick Films
Maverick Films is a film production company known for backing independent and genre-driven movies, including the crime comedy-drama "Gridlock'd."
-
E.
Integral Films
Integral Films is a film production company known for working on projects such as David Cronenberg’s satirical drama "Maps to the Stars."
- 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: MPG Films Triple: [Breach, productionCompany, MPG Films]
Generated description
MPG Films is a film production company known for producing the 2007 legal thriller "Breach."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MPG Films Target entity description: MPG Films is a film production company known for producing the 2007 legal thriller "Breach."
-
A.
M6 Films
M6 Films is a French film production company known for backing popular international action and thriller movies.
-
B.
MPM Film
MPM Film is a film production company known for developing and producing independent and international cinema projects.
-
C.
Lippert Films
Lippert Films was an American independent film distribution and production company active in the mid-20th century, known for handling low-budget genre movies.
-
D.
Maverick Films
Maverick Films is a film production company known for backing independent and genre-driven movies, including the crime comedy-drama "Gridlock'd."
-
E.
Integral Films
Integral Films is a film production company known for working on projects such as David Cronenberg’s satirical drama "Maps to the Stars."
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e666daf73c819089f02ca6faa2c283 |
completed | April 20, 2026, 5:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a082712b04c81908e0413dee9a04ea6 |
completed | May 16, 2026, 8:13 a.m. |
| NEDg | Description generation | batch_6a082864abdc819080a9822114eb8c25 |
completed | May 16, 2026, 8:18 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a082946da0c81909db45f0989020a17 |
completed | May 16, 2026, 8:22 a.m. |
Created at: April 11, 2026, 11:27 p.m.