Triple
T2173065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MASH |
E48466
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
Ingo Preminger
Ingo Preminger was a film producer best known for producing the acclaimed 1970 anti-war black comedy "MASH."
|
E243078
|
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: Ingo Preminger | Statement: [MASH, producer, Ingo Preminger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ingo Preminger Context triple: [MASH, producer, Ingo Preminger]
-
A.
Louis Kraemer
Louis Kraemer was a party to the landmark U.S. Supreme Court case Shelley v. Kraemer, which held that courts could not enforce racially restrictive housing covenants.
-
B.
Paul Henreid
Paul Henreid was an Austrian-born actor and director best known for his role as resistance leader Victor Laszlo in the classic film "Casablanca."
-
C.
Hal Mohr
Hal Mohr was an American cinematographer renowned for his innovative camera work in early Hollywood, notably becoming the only write-in Academy Award winner for his cinematography.
-
D.
Tom Benedek
Tom Benedek is an American screenwriter best known for co-writing the science fiction film "Cocoon."
-
E.
Paul Hirsch
Paul Hirsch is an American film editor renowned for his work on major Hollywood films, including the original Star Wars.
- 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: Ingo Preminger Triple: [MASH, producer, Ingo Preminger]
Generated description
Ingo Preminger was a film producer best known for producing the acclaimed 1970 anti-war black comedy "MASH."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ingo Preminger Target entity description: Ingo Preminger was a film producer best known for producing the acclaimed 1970 anti-war black comedy "MASH."
-
A.
Louis Kraemer
Louis Kraemer was a party to the landmark U.S. Supreme Court case Shelley v. Kraemer, which held that courts could not enforce racially restrictive housing covenants.
-
B.
Paul Henreid
Paul Henreid was an Austrian-born actor and director best known for his role as resistance leader Victor Laszlo in the classic film "Casablanca."
-
C.
Hal Mohr
Hal Mohr was an American cinematographer renowned for his innovative camera work in early Hollywood, notably becoming the only write-in Academy Award winner for his cinematography.
-
D.
Tom Benedek
Tom Benedek is an American screenwriter best known for co-writing the science fiction film "Cocoon."
-
E.
Paul Hirsch
Paul Hirsch is an American film editor renowned for his work on major Hollywood films, including the original Star Wars.
- 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_69a88aa3faa48190995b233af6525815 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abbecb97a48190834e3e536184bbd1 |
completed | March 7, 2026, 5:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae5d9c61448190930777bcf2028882 |
completed | March 9, 2026, 5:41 a.m. |
| NEDg | Description generation | batch_69ae5e1ea6108190b22ead618d620613 |
completed | March 9, 2026, 5:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae5ea7909c8190a93d87a5d07b84d4 |
completed | March 9, 2026, 5:46 a.m. |
Created at: March 4, 2026, 7:45 p.m.