Triple
T6751323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Resistible Rise of Arturo Ui |
E154345
|
entity |
| Predicate | characterBasedOn |
P2004
|
FINISHED |
| Object |
Roma; Ernst Röhm
Ernst Röhm was a German military officer and early Nazi leader who headed the Sturmabteilung (SA) before being executed during the Night of the Long Knives purge.
|
E616187
|
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: Roma; Ernst Röhm | Statement: [The Resistible Rise of Arturo Ui, characterBasedOn, Roma; Ernst Röhm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roma; Ernst Röhm Context triple: [The Resistible Rise of Arturo Ui, characterBasedOn, Roma; Ernst Röhm]
-
A.
Roman, Romania
Roman, Romania is a historic city in northeastern Romania known as a regional cultural and economic center in the Moldavia region.
-
B.
Rometty
Rometty is the surname of Ginni Rometty, the former chairman, president, and CEO of IBM.
-
C.
Rumuola
Rumuola is a prominent urban neighborhood and transport hub in Port Harcourt, Rivers State, Nigeria.
-
D.
Rommen
Rommen is a neighborhood in Oslo, Norway, situated within the Søndre Nordstrand borough.
-
E.
Ruoms
Ruoms is a small commune in the Ardèche department of southern France, known for its scenic riverside setting and outdoor tourism.
- 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: Roma; Ernst Röhm Triple: [The Resistible Rise of Arturo Ui, characterBasedOn, Roma; Ernst Röhm]
Generated description
Ernst Röhm was a German military officer and early Nazi leader who headed the Sturmabteilung (SA) before being executed during the Night of the Long Knives purge.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Roma; Ernst Röhm Target entity description: Ernst Röhm was a German military officer and early Nazi leader who headed the Sturmabteilung (SA) before being executed during the Night of the Long Knives purge.
-
A.
Roman, Romania
Roman, Romania is a historic city in northeastern Romania known as a regional cultural and economic center in the Moldavia region.
-
B.
Rometty
Rometty is the surname of Ginni Rometty, the former chairman, president, and CEO of IBM.
-
C.
Rumuola
Rumuola is a prominent urban neighborhood and transport hub in Port Harcourt, Rivers State, Nigeria.
-
D.
Rommen
Rommen is a neighborhood in Oslo, Norway, situated within the Søndre Nordstrand borough.
-
E.
Ruoms
Ruoms is a small commune in the Ardèche department of southern France, known for its scenic riverside setting and outdoor tourism.
- 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_69c6880ef37881909268a5a7299b9293 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d1dbc3a48190a35df5dad8c630e8 |
completed | March 27, 2026, 6:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c70b1a0d7481908a813fa5c2e1ba6e |
completed | March 27, 2026, 10:56 p.m. |
| NEDg | Description generation | batch_69c70c82a2008190b0f5f859687a7de5 |
completed | March 27, 2026, 11:02 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c70d7e3d748190ace98ad9cb9c425b |
completed | March 27, 2026, 11:06 p.m. |
Created at: March 27, 2026, 2:11 p.m.