Triple

T30528066
Position Surface form Disambiguated ID Type / Status
Subject Helene Nahowski E776910 entity
Predicate hasRelative P367 FINISHED
Object Franz Nahowski
Franz Nahowski was an Austrian civil servant best known as the husband of Helene Nahowski, who was reputed to have been a mistress of composer Gustav Mahler.
 E2294703 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: Franz Nahowski | Statement: [Helene Nahowski, hasRelative, Franz Nahowski]
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: Franz Nahowski
Triple: [Helene Nahowski, hasRelative, Franz Nahowski]
Generated description
Franz Nahowski was an Austrian civil servant best known as the husband of Helene Nahowski, who was reputed to have been a mistress of composer Gustav Mahler.

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_69f2249c11508190ae7e955755ccfb01 completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f68849c7fc81908b8dcb4b108c6b8a completed May 2, 2026, 11:27 p.m.
NED1 Entity disambiguation (via context triple) batch_6a7c104346388190aaefe3832d27014e completed Aug. 12, 2026, 6:18 a.m.
NEDg Description generation batch_6a7c10aac51c8190b436d068a0f6b9ae completed Aug. 12, 2026, 6:20 a.m.
NED2 Entity disambiguation (via description) batch_6a7c10e7fd7c8190bd46ca69783d0885 completed Aug. 12, 2026, 6:21 a.m.
Created at: April 29, 2026, 8:18 p.m.