Triple
T22022301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal (2018 film) |
E543873
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object |
Johannes Bock
Johannes Bock is a film editor known for his work on the 2018 neo-noir thriller "Terminal."
|
E1549558
|
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: Johannes Bock | Statement: [Terminal (2018 film), editedBy, Johannes Bock]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Johannes Bock Context triple: [Terminal (2018 film), editedBy, Johannes Bock]
-
A.
Johannes Schmoelling
Johannes Schmoelling is a German musician and composer best known as a key member of the electronic music group Tangerine Dream during the early 1980s.
-
B.
Friedrich Müller
Friedrich Müller, often called "Maler Müller," was an 18th-century German painter and poet associated with the Sturm und Drang movement.
-
C.
Johann Böhmer
Johann Böhmer was a German scholar best known as the first husband of the writer and intellectual Caroline Schelling (née Michaelis).
-
D.
Rudolf Kaempfe
Rudolf Kaempfe was a German Wehrmacht general during World War II who held several high-ranking command positions on the Eastern Front.
-
E.
Johann Natterer
Johann Natterer was an Austrian naturalist and explorer renowned for his extensive zoological and ethnographic collections gathered during early 19th-century expeditions in Brazil.
- 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: Johannes Bock Triple: [Terminal (2018 film), editedBy, Johannes Bock]
Generated description
Johannes Bock is a film editor known for his work on the 2018 neo-noir thriller "Terminal."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Johannes Bock Target entity description: Johannes Bock is a film editor known for his work on the 2018 neo-noir thriller "Terminal."
-
A.
Johannes Schmoelling
Johannes Schmoelling is a German musician and composer best known as a key member of the electronic music group Tangerine Dream during the early 1980s.
-
B.
Friedrich Müller
Friedrich Müller, often called "Maler Müller," was an 18th-century German painter and poet associated with the Sturm und Drang movement.
-
C.
Johann Böhmer
Johann Böhmer was a German scholar best known as the first husband of the writer and intellectual Caroline Schelling (née Michaelis).
-
D.
Rudolf Kaempfe
Rudolf Kaempfe was a German Wehrmacht general during World War II who held several high-ranking command positions on the Eastern Front.
-
E.
Johann Natterer
Johann Natterer was an Austrian naturalist and explorer renowned for his extensive zoological and ethnographic collections gathered during early 19th-century expeditions in Brazil.
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127c8ac6881909a9e96e0873a3ae2 |
completed | April 28, 2026, 9:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b73cd90048190972ae88b6828f84a |
completed | May 18, 2026, 8:17 p.m. |
| NEDg | Description generation | batch_6a0b7ad64f38819086f403627f196573 |
completed | May 18, 2026, 8:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b7b1cc47081909f58b3462077c323 |
completed | May 18, 2026, 8:48 p.m. |
Created at: April 16, 2026, 8:23 p.m.