Triple
T20339042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ecstasy |
E495690
|
entity |
| Predicate | cinematographyBy |
P1953
|
FINISHED |
| Object |
Jan Stallich
Jan Stallich was a Czech cinematographer known for his work on numerous European films during the early to mid-20th century.
|
E1426227
|
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: Jan Stallich | Statement: [Ecstasy, cinematographyBy, Jan Stallich]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jan Stallich Context triple: [Ecstasy, cinematographyBy, Jan Stallich]
-
A.
Fredric Steinkamp
Fredric Steinkamp was an American film editor best known for his acclaimed work on major Hollywood productions, including the Oscar-winning epic "Out of Africa."
-
B.
Jan Sadeler
Jan Sadeler was a prominent late 16th-century Flemish engraver and printmaker known for his detailed religious and allegorical prints and as a leading member of the influential Sadeler family of artists.
-
C.
Will Staehle
Will Staehle is a graphic designer and illustrator known for his distinctive, stylized book cover designs.
-
D.
Emmy Sonnemann
Emmy Sonnemann was a German stage actress best known as the second wife of Hermann Göring, a leading figure in Nazi Germany.
-
E.
Jan Leike
Jan Leike is an AI researcher known for his work on AI safety and alignment, including influential contributions at DeepMind and OpenAI.
- 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: Jan Stallich Triple: [Ecstasy, cinematographyBy, Jan Stallich]
Generated description
Jan Stallich was a Czech cinematographer known for his work on numerous European films during the early to mid-20th century.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jan Stallich Target entity description: Jan Stallich was a Czech cinematographer known for his work on numerous European films during the early to mid-20th century.
-
A.
Fredric Steinkamp
Fredric Steinkamp was an American film editor best known for his acclaimed work on major Hollywood productions, including the Oscar-winning epic "Out of Africa."
-
B.
Jan Sadeler
Jan Sadeler was a prominent late 16th-century Flemish engraver and printmaker known for his detailed religious and allegorical prints and as a leading member of the influential Sadeler family of artists.
-
C.
Will Staehle
Will Staehle is a graphic designer and illustrator known for his distinctive, stylized book cover designs.
-
D.
Emmy Sonnemann
Emmy Sonnemann was a German stage actress best known as the second wife of Hermann Göring, a leading figure in Nazi Germany.
-
E.
Jan Leike
Jan Leike is an AI researcher known for his work on AI safety and alignment, including influential contributions at DeepMind and OpenAI.
- 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_69e0b4a1a09881908d97270d6971a25a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678342a0081908ede8006eb5506a3 |
completed | April 20, 2026, 7:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08707bbabc81908788f50a96d7c20f |
completed | May 16, 2026, 1:26 p.m. |
| NEDg | Description generation | batch_6a087129ce3c8190a67ac34ec697ad31 |
completed | May 16, 2026, 1:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0871e3573c81908216b5e508374081 |
completed | May 16, 2026, 1:32 p.m. |
Created at: April 16, 2026, 11:23 a.m.