Triple

T38250786
Position Surface form Disambiguated ID Type / Status
Subject Fragmente – Stille, an Diotima E1014042 entity
Predicate performanceChallenge P183865 FINISHED
Object control of very soft dynamics LITERAL 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: control of very soft dynamics | Statement: [Fragmente – Stille, an Diotima, performanceChallenge, control of very soft dynamics]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: performanceChallenge
Context triple: [Fragmente – Stille, an Diotima, performanceChallenge, control of very soft dynamics]
  • A. challengeType
    Indicates the specific category or kind of challenge associated with an action or relationship between entities.
  • B. activityChallenged
    Indicates that one entity has questioned, disputed, or formally contested the validity, appropriateness, or outcome of an activity involving another entity.
  • C. challengeTo
    Indicates that one entity issues a challenge or dare for another entity to face or respond to.
  • D. challengeUndertaken
    Indicates that an entity has accepted and is actively engaging in a specific challenge or demanding task.
  • E. challengeFor chosen
    Indicates that one entity presents a difficulty, test, or obstacle that must be faced or overcome by another entity.
  • F. None of above.

Provenance (3 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_69f76dd7e89c8190b7866bc85aea521b completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69ff6c061c6c81909ff485e9cafc88a2 completed May 9, 2026, 5:16 p.m.
PD Predicate disambiguation batch_69ff6aaf886c8190a3c87d089453f3de completed May 9, 2026, 5:11 p.m.
Created at: May 3, 2026, 4:30 p.m.