Triple

T19786121
Position Surface form Disambiguated ID Type / Status
Subject Frankenberg, Hesse E475272 entity
Predicate hasRiver P165 FINISHED
Object Eder 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: Eder | Statement: [Frankenberg, Hesse, hasRiver, Eder]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eder
Context triple: [Frankenberg, Hesse, hasRiver, Eder]
  • A. Eder chosen
    The Eder is a river in central Germany that flows through the state of Hesse before joining the Fulda River.
  • B. Éder
    Éder is a Portuguese footballer best known for scoring the extra-time winning goal that secured Portugal’s first major international trophy at UEFA Euro 2016.
  • C. Carrascal
    Carrascal is a coastal municipality in the province of Surigao del Sur in the Philippines, known for its mining industry and fishing communities.
  • D. Estévez
    Estévez is the original Spanish family name of actor Martin Sheen, also shared by several of his children in the entertainment industry.
  • E. Goleto
    Goleto is a historic monastic site in southern Italy, known for its medieval abbey founded in the 12th century.
  • 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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65387d3348190a31f9c2f9bc1c6d9 completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:49 p.m.