Triple

T16821446
Position Surface form Disambiguated ID Type / Status
Subject Alt-Berlin E408901 entity
Predicate contains P35 FINISHED
Object Marienkirche E186190 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: Marienkirche | Statement: [Alt-Berlin, contains, Marienkirche]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marienkirche
Context triple: [Alt-Berlin, contains, Marienkirche]
  • A. Marienkirche chosen
    Marienkirche is a historic medieval church in central Berlin, known as one of the city’s oldest surviving churches and a notable example of Brick Gothic architecture.
  • B. Marienkirche
    Marienkirche is a historic church in the German town of Wolfenbüttel, notable for its architectural and cultural significance.
  • C. Marienkirche
    Marienkirche is a historic St. Mary’s Church located in the German town of Mühlhausen, known for its Gothic architecture and cultural significance.
  • D. Michaelerkirche
    Michaelerkirche is a historic Roman Catholic church in the Austrian city of Steyr, noted for its prominent architecture and cultural significance.
  • E. Petrikirche
    Petrikirche was a historic parish church in the former city of Cölln (now part of central Berlin), notable as one of the oldest and most important medieval churches in the area before its demolition.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d88394566c8190b3dcbdc72935f7fa completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b2e6b59c8190ad562a80e71ce54c completed April 18, 2026, 4:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b29a3854819099eed580eea5d84d completed May 10, 2026, 4:30 p.m.
Created at: April 10, 2026, 5:23 a.m.