Triple

T15105030
Position Surface form Disambiguated ID Type / Status
Subject Hermann von Salza E360767 entity
Predicate familyName P18 FINISHED
Object von Salza
von Salza is a German noble family name historically associated with figures such as Hermann von Salza, a prominent Grand Master of the Teutonic Order.
E1136287 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: von Salza | Statement: [Hermann von Salza, familyName, von Salza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: von Salza
Context triple: [Hermann von Salza, familyName, von Salza]
  • A. Salza
    The Salza is a river in Austria known for its clear waters and scenic gorges, popular for whitewater sports and flowing into the Enns River.
  • B. von Schlebrügge
    von Schlebrügge is the aristocratic German-Swedish family name of Nena von Schlebrügge, a former fashion model and mother of actress Uma Thurman.
  • C. Salez
    Salez is a village in the municipality of Sennwald in the canton of St. Gallen, Switzerland.
  • D. von Sonnenthal
    Von Sonnenthal is a German-language surname historically associated with notable figures in Central European theater and culture.
  • E. Vinzgouw
    Vinzgouw was a medieval Frankish region associated with the early life and family origins of Hildegard, the wife of Charlemagne.
  • 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: von Salza
Triple: [Hermann von Salza, familyName, von Salza]
Generated description
von Salza is a German noble family name historically associated with figures such as Hermann von Salza, a prominent Grand Master of the Teutonic Order.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: von Salza
Target entity description: von Salza is a German noble family name historically associated with figures such as Hermann von Salza, a prominent Grand Master of the Teutonic Order.
  • A. Salza
    The Salza is a river in Austria known for its clear waters and scenic gorges, popular for whitewater sports and flowing into the Enns River.
  • B. von Schlebrügge
    von Schlebrügge is the aristocratic German-Swedish family name of Nena von Schlebrügge, a former fashion model and mother of actress Uma Thurman.
  • C. Salez
    Salez is a village in the municipality of Sennwald in the canton of St. Gallen, Switzerland.
  • D. von Sonnenthal
    Von Sonnenthal is a German-language surname historically associated with notable figures in Central European theater and culture.
  • E. Vinzgouw
    Vinzgouw was a medieval Frankish region associated with the early life and family origins of Hildegard, the wife of Charlemagne.
  • 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_69d85a0491ec8190830960be8fafb994 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00588f35481909674f161bf0f3918 completed April 15, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69feae28e99881908156909e553c2538 completed May 9, 2026, 3:46 a.m.
NEDg Description generation batch_69feaf39ddec81908da194211b2d0994 completed May 9, 2026, 3:51 a.m.
NED2 Entity disambiguation (via description) batch_69feafce7fa081908bc6167970f1822f completed May 9, 2026, 3:53 a.m.
Created at: April 10, 2026, 3:05 a.m.