Triple
T10573855
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragnet (film, 1987) |
E249560
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object |
Pep Streebek
Pep Streebek is a brash, irreverent young detective who partners with the strait-laced Joe Friday in the 1987 comedy film "Dragnet."
|
E871656
|
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: Pep Streebek | Statement: [Dragnet (film, 1987), character, Pep Streebek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pep Streebek Context triple: [Dragnet (film, 1987), character, Pep Streebek]
-
A.
Adrian Sweere
Adrian Sweere was an early 20th-century Jesuit priest and educator who played a key role in establishing what would become Seattle University.
-
B.
Dirk Roosenburg
Dirk Roosenburg was a prominent Dutch architect known for his early 20th-century modernist designs and as the grandfather of architect Rem Koolhaas.
-
C.
Tom Heskes
Tom Heskes is a machine learning researcher and professor known for his work in probabilistic modeling, Bayesian methods, and neural networks.
-
D.
Jeroen van der Boom
Jeroen van der Boom is a Dutch singer, television presenter, and entertainer known for his successful music career and prominent roles on Dutch TV talent shows.
-
E.
Sven Groeneveld
Sven Groeneveld is a Dutch professional tennis coach known for working with numerous top-ranked players on the WTA and ATP tours.
- 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: Pep Streebek Triple: [Dragnet (film, 1987), character, Pep Streebek]
Generated description
Pep Streebek is a brash, irreverent young detective who partners with the strait-laced Joe Friday in the 1987 comedy film "Dragnet."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Pep Streebek Target entity description: Pep Streebek is a brash, irreverent young detective who partners with the strait-laced Joe Friday in the 1987 comedy film "Dragnet."
-
A.
Adrian Sweere
Adrian Sweere was an early 20th-century Jesuit priest and educator who played a key role in establishing what would become Seattle University.
-
B.
Dirk Roosenburg
Dirk Roosenburg was a prominent Dutch architect known for his early 20th-century modernist designs and as the grandfather of architect Rem Koolhaas.
-
C.
Tom Heskes
Tom Heskes is a machine learning researcher and professor known for his work in probabilistic modeling, Bayesian methods, and neural networks.
-
D.
Jeroen van der Boom
Jeroen van der Boom is a Dutch singer, television presenter, and entertainer known for his successful music career and prominent roles on Dutch TV talent shows.
-
E.
Sven Groeneveld
Sven Groeneveld is a Dutch professional tennis coach known for working with numerous top-ranked players on the WTA and ATP tours.
- 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d5274929cc81909a79d5e2049f7389 |
completed | April 7, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d94b5d89748190bb398943e4a16e9b |
completed | April 10, 2026, 7:11 p.m. |
| NEDg | Description generation | batch_69d94e1502108190a81bfa1d5a425e5a |
completed | April 10, 2026, 7:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d94f0bb6888190b4038df6dcd96d33 |
completed | April 10, 2026, 7:27 p.m. |
Created at: April 6, 2026, 12:37 p.m.