Triple

T27978284
Position Surface form Disambiguated ID Type / Status
Subject cursed soldiers E706547 entity
Predicate participant P858 FINISHED
Object Józef Franczak
Józef Franczak was a Polish anti-communist resistance fighter, often regarded as one of the last surviving members of the post-World War II underground known as the "cursed soldiers."
E2042656 NE FINISHED

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: Józef Franczak | Statement: [cursed soldiers, participant, Józef Franczak]
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: Józef Franczak
Triple: [cursed soldiers, participant, Józef Franczak]
Generated description
Józef Franczak was a Polish anti-communist resistance fighter, often regarded as one of the last surviving members of the post-World War II underground known as the "cursed soldiers."

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_69ef96b7f330819090f315318ba6977e completed April 27, 2026, 5:02 p.m.
NER Named-entity recognition batch_69f63b661b8081908abaf92cde6ab125 completed May 2, 2026, 5:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3538e60ed481908835cc9a4ac5996d completed June 19, 2026, 12:41 p.m.
NEDg Description generation batch_6a3539d6f5448190aee35547822a99ff completed June 19, 2026, 12:45 p.m.
NED2 Entity disambiguation (via description) batch_6a353abc2f7c8190bb5843c25bb84256 completed June 19, 2026, 12:49 p.m.
Created at: April 27, 2026, 7:42 p.m.