Triple
T20407527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cross of Iron |
E500509
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Fred Stillkrauth
Fred Stillkrauth was a German actor known for his supporting roles in films such as Sam Peckinpah’s World War II drama "Cross of Iron."
|
E1429318
|
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: Fred Stillkrauth | Statement: [Cross of Iron, starring, Fred Stillkrauth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fred Stillkrauth Context triple: [Cross of Iron, starring, Fred Stillkrauth]
-
A.
Michael Bruhn
Michael Bruhn is a person notable enough to be recognized as a namesake of the surname Bruhn, though specific widely known public details about him are not clearly established.
-
B.
William Diehl
William Diehl was an American novelist best known for his gritty, suspenseful legal and crime thrillers.
-
C.
Michael Ballhaus
Michael Ballhaus was a renowned German cinematographer celebrated for his dynamic camera work and frequent collaborations with director Martin Scorsese.
-
D.
Fred Schuler
Fred Schuler is a cinematographer best known for his work on films such as the 1980 comedy "Stir Crazy."
-
E.
Carl Nafzger
Carl Nafzger is an American Thoroughbred racehorse trainer best known for conditioning champions such as Kentucky Derby winner Unbridled.
- 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: Fred Stillkrauth Triple: [Cross of Iron, starring, Fred Stillkrauth]
Generated description
Fred Stillkrauth was a German actor known for his supporting roles in films such as Sam Peckinpah’s World War II drama "Cross of Iron."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Fred Stillkrauth Target entity description: Fred Stillkrauth was a German actor known for his supporting roles in films such as Sam Peckinpah’s World War II drama "Cross of Iron."
-
A.
Michael Bruhn
Michael Bruhn is a person notable enough to be recognized as a namesake of the surname Bruhn, though specific widely known public details about him are not clearly established.
-
B.
William Diehl
William Diehl was an American novelist best known for his gritty, suspenseful legal and crime thrillers.
-
C.
Michael Ballhaus
Michael Ballhaus was a renowned German cinematographer celebrated for his dynamic camera work and frequent collaborations with director Martin Scorsese.
-
D.
Fred Schuler
Fred Schuler is a cinematographer best known for his work on films such as the 1980 comedy "Stir Crazy."
-
E.
Carl Nafzger
Carl Nafzger is an American Thoroughbred racehorse trainer best known for conditioning champions such as Kentucky Derby winner Unbridled.
- 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_69e0b4a81bec8190b69adfdc1336a015 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67993dc7081908ebd54ec92e712ea |
completed | April 20, 2026, 7:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a087b1db4ec8190933e26fbb2003dce |
completed | May 16, 2026, 2:11 p.m. |
| NEDg | Description generation | batch_6a088015c514819087967845614dd25d |
completed | May 16, 2026, 2:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0880b79edc81908b180db5338f57db |
completed | May 16, 2026, 2:35 p.m. |
Created at: April 16, 2026, 11:29 a.m.