Triple

T3271237
Position Surface form Disambiguated ID Type / Status
Subject William I, Elector of Hesse E68652 entity
Predicate placeOfBirth P1 FINISHED
Object Kassel E210960 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: Kassel | Statement: [William I, Elector of Hesse, placeOfBirth, Kassel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kassel
Context triple: [William I, Elector of Hesse, placeOfBirth, Kassel]
  • A. Kassel chosen
    Kassel is a city in central Germany known for its cultural institutions and as the host of the renowned contemporary art exhibition documenta.
  • B. Gießen
    Gießen is a mid-sized university city in central Germany known for its academic institutions and role as a regional administrative and cultural center.
  • C. Erfurt
    Erfurt is a historic German city in the state of Thuringia, known for its well-preserved medieval old town and as an important cultural and educational center.
  • D. Wetzlar
    Wetzlar is a historic German city in the state of Hesse, known for its medieval old town and its long tradition in optics and precision engineering.
  • E. Karlsruhe
    Karlsruhe is a major city in southwestern Germany best known as the seat of the country’s highest courts and a central hub of German constitutional jurisprudence.
  • 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_69ad859b54f881909bf530d549caf2fd completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adaff4b9dc8190b7e3da0bbffccf99 completed March 8, 2026, 5:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69bfaf20b6408190ae0ab543361a0eb2 completed March 22, 2026, 8:58 a.m.
Created at: March 8, 2026, 3:09 p.m.