Triple

T17210473
Position Surface form Disambiguated ID Type / Status
Subject PWSFTviT E417713 entity
Predicate hasAlumni P51 FINISHED
Object Piotr Sobociński NE NERFINISHED

How this triple was built (2 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: Piotr Sobociński | Statement: [PWSFTviT, hasAlumni, Piotr Sobociński]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Piotr Sobociński
Context triple: [PWSFTviT, hasAlumni, Piotr Sobociński]
  • A. Piotr Sobociński chosen
    Piotr Sobociński was a Polish cinematographer known for his visually expressive work on both European art films and major Hollywood productions.
  • B. Wojciech Sosnowski
    Wojciech Sosnowski, better known by his stage name Sokół, is a prominent Polish rapper, songwriter, and music producer recognized as one of the key figures in Poland’s hip-hop scene.
  • C. Cezary Skubiszewski
    Cezary Skubiszewski is a Polish-born Australian composer known for his acclaimed film and television scores.
  • D. Piotr Lipski
    Piotr Lipski is a person bearing the Polish surname Lipski, though no widely documented public information distinguishes him as a notable figure.
  • E. Jerzy Podbrożny
    Jerzy Podbrożny is a former Polish footballer and forward known for his successful club career in Poland and his stint in Major League Soccer in the late 1990s.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d886d779488190b131369541c04e7d completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42dc4792081909443df7937768ede completed April 19, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:38 a.m.