Triple

T19565380
Position Surface form Disambiguated ID Type / Status
Subject Eschen E489567 entity
Predicate hasBorderWith P224 FINISHED
Object Gamprin 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: Gamprin | Statement: [Eschen, hasBorderWith, Gamprin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gamprin
Context triple: [Eschen, hasBorderWith, Gamprin]
  • A. Gamprin chosen
    Gamprin is a small municipality in the western part of Liechtenstein, known for its rural character and location along the Rhine River.
  • B. Grimonprez
    Grimonprez is the namesake of the French football stadium Stade Grimonprez-Jooris, likely a notable local figure associated with the Lille area.
  • C. Osphranter
    Osphranter is a genus of large Australian marsupials that includes several species of kangaroos and wallaroos.
  • D. Ormur
    Ormur is a lesser-known Eastern Iranian language spoken primarily by the Ormur people in parts of Afghanistan and Pakistan.
  • E. Puygros
    Puygros is a small French village located in the Alpine foothills within the Massif des Bauges region of southeastern France.
  • 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63f777cf081909312b46ac09bce7c completed April 20, 2026, 3 p.m.
Created at: April 10, 2026, 1:42 p.m.