Triple

T3168811
Position Surface form Disambiguated ID Type / Status
Subject The Song of Bernadette E66276 entity
Predicate starring P1507 FINISHED
Object Roman Bohnen
Roman Bohnen was an American character actor active in the 1930s and 1940s, known for his supporting roles in both Hollywood films and on the stage.
E335914 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: Roman Bohnen | Statement: [The Song of Bernadette, starring, Roman Bohnen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roman Bohnen
Context triple: [The Song of Bernadette, starring, Roman Bohnen]
  • A. Bryan Devendorf
    Bryan Devendorf is an American drummer best known as a founding member and rhythmic backbone of the indie rock band The National.
  • B. Ken Daurio
    Ken Daurio is an American screenwriter best known for co-writing popular animated films such as Despicable Me, The Lorax, and The Secret Life of Pets.
  • C. Brant Daugherty
    Brant Daugherty is an American actor known for his roles in television series like "Pretty Little Liars" and films including the "Fifty Shades" franchise.
  • D. Marcus T. Paulk
    Marcus T. Paulk is an American actor and rapper best known for his role as Myles Mitchell on the television sitcom "Moesha."
  • E. Ian Bader
    Ian Bader is a prominent architect and partner at the international architecture firm Pei Cobb Freed & Partners.
  • 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: Roman Bohnen
Triple: [The Song of Bernadette, starring, Roman Bohnen]
Generated description
Roman Bohnen was an American character actor active in the 1930s and 1940s, known for his supporting roles in both Hollywood films and on the stage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Roman Bohnen
Target entity description: Roman Bohnen was an American character actor active in the 1930s and 1940s, known for his supporting roles in both Hollywood films and on the stage.
  • A. Bryan Devendorf
    Bryan Devendorf is an American drummer best known as a founding member and rhythmic backbone of the indie rock band The National.
  • B. Ken Daurio
    Ken Daurio is an American screenwriter best known for co-writing popular animated films such as Despicable Me, The Lorax, and The Secret Life of Pets.
  • C. Brant Daugherty
    Brant Daugherty is an American actor known for his roles in television series like "Pretty Little Liars" and films including the "Fifty Shades" franchise.
  • D. Marcus T. Paulk
    Marcus T. Paulk is an American actor and rapper best known for his role as Myles Mitchell on the television sitcom "Moesha."
  • E. Ian Bader
    Ian Bader is a prominent architect and partner at the international architecture firm Pei Cobb Freed & Partners.
  • 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_69ad8585d7988190af37365331093ccd completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada64726048190933dbdc44258703e completed March 8, 2026, 4:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b24b552b488190938ed9fe4d046b01 completed March 12, 2026, 5:12 a.m.
NEDg Description generation batch_69b24ecd84648190a098b7057321f1f1 completed March 12, 2026, 5:27 a.m.
NED2 Entity disambiguation (via description) batch_69b24f1d6aa081909e4271f4314e2f3f completed March 12, 2026, 5:29 a.m.
Created at: March 8, 2026, 3:06 p.m.