Triple

T17625038
Position Surface form Disambiguated ID Type / Status
Subject Principality of Nassau-Usingen E429817 entity
Predicate capital P234 FINISHED
Object Usingen E209322 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: Usingen | Statement: [Principality of Nassau-Usingen, capital, Usingen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Usingen
Context triple: [Principality of Nassau-Usingen, capital, Usingen]
  • A. Usingen chosen
    Usingen is a small historic town in the Hochtaunus district of Hesse, Germany, known for its picturesque setting in the Taunus hills and its traditional German architecture.
  • B. Tavarede
    Tavarede is a civil parish within the municipality of Figueira da Foz in central Portugal, known for its residential character and local cultural traditions.
  • C. Areuse
    Areuse is a river in western Switzerland that flows through the Jura Mountains and picturesque gorges before emptying into Lake Neuchâtel.
  • D. Userin
    Userin is a small settlement in the Mecklenburgische Seenplatte region of Mecklenburg-Vorpommern in northeastern Germany.
  • E. Uesen
    Uesen is a district or locality within the town of Achim in Lower Saxony, Germany.
  • 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_69d889e37f308190a6aa0a69daff86c7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46dbc62e88190b9757dc7c52d7fee completed April 19, 2026, 5:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a020a9714e081909283b932dc5d9301 completed May 11, 2026, 4:57 p.m.
Created at: April 10, 2026, 5:52 a.m.