Triple

T16497266
Position Surface form Disambiguated ID Type / Status
Subject Walter Reisch E400715 entity
Predicate spouse P13 FINISHED
Object Poldi Dur
Poldi Dur was an Austrian actress known for her work in early 20th-century German-language cinema and theatre.
E1217124 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: Poldi Dur | Statement: [Walter Reisch, spouse, Poldi Dur]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Poldi Dur
Context triple: [Walter Reisch, spouse, Poldi Dur]
  • A. Poldi
    Poldi is a common German diminutive nickname for the given name Leopold.
  • B. Rudi
    Rudi is a common diminutive form of the given name Rudolf, used in various European languages.
  • C. Rudi
    Rudi is the official mascot of the Cleveland Gladiators arena football team, known for energizing fans at games and team events.
  • D. Rolph
    Rolph is a surname most notably associated with James Rolph, a prominent early 20th-century American politician and former mayor of San Francisco and governor of California.
  • E. Erwin
    Erwin is a masculine given name of German origin, historically associated with figures such as the World War II field marshal Erwin Rommel.
  • 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: Poldi Dur
Triple: [Walter Reisch, spouse, Poldi Dur]
Generated description
Poldi Dur was an Austrian actress known for her work in early 20th-century German-language cinema and theatre.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Poldi Dur
Target entity description: Poldi Dur was an Austrian actress known for her work in early 20th-century German-language cinema and theatre.
  • A. Poldi
    Poldi is a common German diminutive nickname for the given name Leopold.
  • B. Rudi
    Rudi is a common diminutive form of the given name Rudolf, used in various European languages.
  • C. Rudi
    Rudi is the official mascot of the Cleveland Gladiators arena football team, known for energizing fans at games and team events.
  • D. Rolph
    Rolph is a surname most notably associated with James Rolph, a prominent early 20th-century American politician and former mayor of San Francisco and governor of California.
  • E. Erwin
    Erwin is a masculine given name of German origin, historically associated with figures such as the World War II field marshal Erwin Rommel.
  • 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_69d88381f6148190819958a038be990e completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e343a7c81909e04cbaaa40e2531 completed April 18, 2026, 7:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00582a316c81908ec32679c976ba23 completed May 10, 2026, 10:04 a.m.
NEDg Description generation batch_6a0058d08f048190b83d3fb69ba8a2c3 completed May 10, 2026, 10:07 a.m.
NED2 Entity disambiguation (via description) batch_6a0059b5a1f8819089caefc121246739 completed May 10, 2026, 10:11 a.m.
Created at: April 10, 2026, 5:14 a.m.