Triple

T20960995
Position Surface form Disambiguated ID Type / Status
Subject Homberg (Efze) E516242 entity
Predicate locatedOn P40 FINISHED
Object Efze 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: Efze | Statement: [Homberg (Efze), locatedOn, Efze]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Efze
Context triple: [Homberg (Efze), locatedOn, Efze]
  • A. Efze chosen
    Efze is a small river in the German state of Hesse that flows through the town of Homberg (Efze).
  • B. Zafonic
    Zafonic was a champion European Thoroughbred racehorse best known for his brilliant speed and record-breaking victory in the 2000 Guineas.
  • C. Nefza
    Nefza is a town in northwestern Tunisia known for its forests, lakes, and proximity to the Mediterranean coast within the Béja Governorate.
  • D. Effe
    Effe is the popular nickname of Fortitudo Bologna, a historic Italian professional basketball club known for its passionate fan base and intense rivalries.
  • E. Ebikon
    Ebikon is a municipality in the canton of Lucerne in central Switzerland, situated in the Reuss Valley near the city of Lucerne.
  • 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_69e0b4fde6c48190af1398e7e734629e completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fb6f134081908b1ed48ce708f3d5 completed April 21, 2026, 4:22 a.m.
Created at: April 16, 2026, 1:31 p.m.