Triple

T12849521
Position Surface form Disambiguated ID Type / Status
Subject Martin Bormann E307273 entity
Predicate placeOfBirth P1 FINISHED
Object Wegeleben E307273 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: Wegeleben | Statement: [Martin Bormann, placeOfBirth, Wegeleben]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wegeleben
Context triple: [Martin Bormann, placeOfBirth, Wegeleben]
  • A. Wegeleben chosen
    Wegeleben is a small town in the Harz district of Saxony-Anhalt, Germany, historically noted as the birthplace of high-ranking Nazi official Martin Bormann.
  • B. Rämistrasse
    Rämistrasse is a major street in central Zurich, Switzerland, known for hosting key university buildings and cultural institutions.
  • C. Duenweg
    Duenweg is a small city located in Jasper County in southwestern Missouri, United States.
  • D. Salzstraße
    Salzstraße is a historic street in Münster, Germany, known as one of the city’s traditional merchant and baroque thoroughfares.
  • E. Saarbahn
    Saarbahn is a regional light rail and tram-train operator based in Saarbrücken, Germany, providing cross-border public transport services into neighboring regions such as Luxembourg and France.
  • 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_69d7bdf5e7cc8190be357278bc5ba3bb completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9701fe684819084582d1b4c809429 completed April 10, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f69ba5059c81908be3b8b371518f41 completed May 3, 2026, 12:49 a.m.
Created at: April 9, 2026, 5:36 p.m.