Triple

T33363773
Position Surface form Disambiguated ID Type / Status
Subject Socialist Reich Party E854293 entity
Predicate foundedBy P104 FINISHED
Object Fritz Rössler
Fritz Rössler was a German far-right politician best known as a leading figure in postwar neo-Nazism and a founder of the Socialist Reich Party.
E2296009 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: Fritz Rössler | Statement: [Socialist Reich Party, foundedBy, Fritz Rössler]
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: Fritz Rössler
Triple: [Socialist Reich Party, foundedBy, Fritz Rössler]
Generated description
Fritz Rössler was a German far-right politician best known as a leading figure in postwar neo-Nazism and a founder of the Socialist Reich Party.

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_69f3496bda8c8190bfc8fade9d1b791c completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f6dfcc271081908f920d49ff201019 completed May 3, 2026, 5:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a82233ef8e88190a0a2bb8cf1f1f688 completed Aug. 16, 2026, 8:53 p.m.
NEDg Description generation batch_6a8223900b8c8190beb7de98ce0f1683 completed Aug. 16, 2026, 8:54 p.m.
NED2 Entity disambiguation (via description) batch_6a8223bec9348190a16fb30e796c36bd completed Aug. 16, 2026, 8:55 p.m.
Created at: May 1, 2026, 1:34 a.m.