Triple

T19592778
Position Surface form Disambiguated ID Type / Status
Subject Carillon Berlin E470276 entity
Predicate isCulturalSite P28782 FINISHED
Object true 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: true | Statement: [Carillon Berlin, isCulturalSite, true]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: isCulturalSite
Context triple: [Carillon Berlin, isCulturalSite, true]
  • A. isCulturalHeritageSite
    Indicates that a place or structure is officially recognized and protected as having significant cultural, historical, or artistic value.
  • B. culturalSite chosen
    Indicates that one entity is recognized or designated as a cultural site associated with or located in relation to another entity.
  • C. hasCulturalSiteType
    Indicates that an entity is associated with, or classified by, a specific type or category of cultural site.
  • D. hasUNESCOCandidateSite
    Indicates that an entity possesses or includes at least one site that is a candidate for inscription on the UNESCO World Heritage List.
  • E. containsCulturalHeritageSite
    Indicates that a place or area includes within its boundaries at least one recognized cultural heritage site.
  • 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_69d8e510024481908415c0d616fa6186 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e64057460c8190962e2e58f06b3985 completed April 20, 2026, 3:03 p.m.
PD Predicate disambiguation batch_69e514dbdb988190b55931a8138c73e7 completed April 19, 2026, 5:46 p.m.
Created at: April 10, 2026, 1:43 p.m.