Triple

T17440685
Position Surface form Disambiguated ID Type / Status
Subject Georgstraße E424141 entity
Predicate connectsTo P845 FINISHED
Object Steintor NE NERFINISHED

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: Steintor | Statement: [Georgstraße, connectsTo, Steintor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steintor
Context triple: [Georgstraße, connectsTo, Steintor]
  • A. Steintor (Stone Gate) chosen
    Steintor (Stone Gate) is a historic city gate and landmark in Hanover, Germany, that once formed part of the medieval fortifications and now lends its name to the surrounding square and district.
  • B. Steintor city gate
    The Steintor city gate is a historic medieval gate in Anklam, Germany, and one of the town’s most prominent architectural landmarks.
  • C. Stargarder Tor
    Stargarder Tor is a well-preserved medieval brick city gate in Neubrandenburg, Germany, renowned as one of the city's iconic defensive structures.
  • D. Störnstein
    Störnstein is a small municipality in the Upper Palatinate region of Bavaria, Germany.
  • E. Spiterstulen
    Spiterstulen is a mountain lodge in Norway’s Jotunheimen region that serves as a key base for hikers and climbers exploring nearby peaks.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889d88b6081908bada047f5b3ba51 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44ff75538819083f77756d39a1aaa completed April 19, 2026, 3:45 a.m.
Created at: April 10, 2026, 5:46 a.m.