Triple

T5821734
Position Surface form Disambiguated ID Type / Status
Subject Katyn (2007 film) E129123 entity
Predicate hasCastMember P2308 FINISHED
Object Władysław Kowalski
Władysław Kowalski was a Polish film and theater actor known for his extensive career in Polish cinema and stage productions.
E547062 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: Władysław Kowalski | Statement: [Katyn (2007 film), hasCastMember, Władysław Kowalski]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Władysław Kowalski
Context triple: [Katyn (2007 film), hasCastMember, Władysław Kowalski]
  • A. Tomasz Kowalski
    Tomasz Kowalski was a Polish high-altitude mountaineer known for co-achieving the historic first winter ascent of Broad Peak in the Karakoram.
  • B. Czesław
    Czesław is a Polish masculine given name, historically borne by notable figures such as Nobel Prize–winning poet Czesław Miłosz.
  • C. Kowale Oleckie
    Kowale Oleckie is a village in northern Poland that serves as the seat of its local administrative district within the Warmian-Masurian Voivodeship.
  • D. Józef
    Józef is a masculine given name of Hebrew origin, widely used in Poland and other Slavic countries as a form of Joseph.
  • E. Janusz Laskowski
    Janusz Laskowski is a Polish professional associated with Wrocław University of Science and Technology, recognized as one of its notable alumni.
  • 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: Władysław Kowalski
Triple: [Katyn (2007 film), hasCastMember, Władysław Kowalski]
Generated description
Władysław Kowalski was a Polish film and theater actor known for his extensive career in Polish cinema and stage productions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Władysław Kowalski
Target entity description: Władysław Kowalski was a Polish film and theater actor known for his extensive career in Polish cinema and stage productions.
  • A. Tomasz Kowalski
    Tomasz Kowalski was a Polish high-altitude mountaineer known for co-achieving the historic first winter ascent of Broad Peak in the Karakoram.
  • B. Czesław
    Czesław is a Polish masculine given name, historically borne by notable figures such as Nobel Prize–winning poet Czesław Miłosz.
  • C. Kowale Oleckie
    Kowale Oleckie is a village in northern Poland that serves as the seat of its local administrative district within the Warmian-Masurian Voivodeship.
  • D. Józef
    Józef is a masculine given name of Hebrew origin, widely used in Poland and other Slavic countries as a form of Joseph.
  • E. Janusz Laskowski
    Janusz Laskowski is a Polish professional associated with Wrocław University of Science and Technology, recognized as one of its notable alumni.
  • 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_69c0084869e881908d7859492183ca7b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c033e7403881908f5e3fe40183865a completed March 22, 2026, 6:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69c09856bd7881909bf6a87e0c071103 completed March 23, 2026, 1:33 a.m.
NEDg Description generation batch_69c098f465cc819088241200306bd273 completed March 23, 2026, 1:35 a.m.
NED2 Entity disambiguation (via description) batch_69c09978ab548190934bc9517444f8a7 completed March 23, 2026, 1:38 a.m.
Created at: March 22, 2026, 3:53 p.m.