Triple

T13796544
Position Surface form Disambiguated ID Type / Status
Subject Keoma E331531 entity
Predicate castMember P1668 FINISHED
Object William Berger
William Berger was an Austrian-born actor best known for his prolific work in Italian genre cinema, particularly Spaghetti Westerns of the 1960s and 1970s.
E1070109 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: William Berger | Statement: [Keoma, castMember, William Berger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Berger
Context triple: [Keoma, castMember, William Berger]
  • A. Albert Berger
    Albert Berger is an American film producer known for acclaimed independent and studio films, including the Oscar-winning drama "Cold Mountain."
  • B. Louis Fischer
    Louis Fischer was an American entrepreneur best known as the founder of the Gino's Hamburgers fast-food restaurant chain.
  • C. Edward Berger
    Edward Berger is a German film and television director known for his acclaimed work on series like "Patrick Melrose" and the Oscar-winning war drama "All Quiet on the Western Front."
  • D. Walter Blum
    Walter Blum is a German mathematician known for his contributions to algebra and mathematical education.
  • E. Charles Schoenbaum
    Charles Schoenbaum was an American cinematographer known for his work on numerous Hollywood films during the mid-20th century.
  • 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: William Berger
Triple: [Keoma, castMember, William Berger]
Generated description
William Berger was an Austrian-born actor best known for his prolific work in Italian genre cinema, particularly Spaghetti Westerns of the 1960s and 1970s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: William Berger
Target entity description: William Berger was an Austrian-born actor best known for his prolific work in Italian genre cinema, particularly Spaghetti Westerns of the 1960s and 1970s.
  • A. Albert Berger
    Albert Berger is an American film producer known for acclaimed independent and studio films, including the Oscar-winning drama "Cold Mountain."
  • B. Louis Fischer
    Louis Fischer was an American entrepreneur best known as the founder of the Gino's Hamburgers fast-food restaurant chain.
  • C. Edward Berger
    Edward Berger is a German film and television director known for his acclaimed work on series like "Patrick Melrose" and the Oscar-winning war drama "All Quiet on the Western Front."
  • D. Walter Blum
    Walter Blum is a German mathematician known for his contributions to algebra and mathematical education.
  • E. Charles Schoenbaum
    Charles Schoenbaum was an American cinematographer known for his work on numerous Hollywood films during the mid-20th century.
  • 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_69d81c58feb08190a77bca8bf7d6d20f completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de025be1f08190aac525d72d7dc0c3 completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce667c248190a9d0a0f1e9e228ae completed May 3, 2026, 10:38 p.m.
NEDg Description generation batch_69f9fd56da288190b2bd33bc496c3fb9 completed May 5, 2026, 2:23 p.m.
NED2 Entity disambiguation (via description) batch_69fb039fdb1c8190ad5286d1cfe80a29 completed May 6, 2026, 9:02 a.m.
Created at: April 9, 2026, 10:11 p.m.