Triple

T19869805
Position Surface form Disambiguated ID Type / Status
Subject B33 road E477482 entity
Predicate passesThrough P225 FINISHED
Object Stockach 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: Stockach | Statement: [B33 road, passesThrough, Stockach]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stockach
Context triple: [B33 road, passesThrough, Stockach]
  • A. Stockach chosen
    Stockach is a small town in southern Germany’s Baden-Württemberg state, situated near Lake Constance and known historically as a regional administrative and market center.
  • B. Aagje
    Aagje is a Dutch feminine given name, traditionally used as a diminutive or variant of names like Agatha.
  • C. Heckerling
    Heckerling is the surname of American film director and screenwriter Amy Heckerling, known for works like "Fast Times at Ridgemont High" and "Clueless."
  • D. Fink
    Fink is a British singer-songwriter and producer known for his atmospheric blend of folk, blues, and electronic music.
  • E. Fink
    Fink is an open-source package management system that brings a wide range of Unix and open-source software to macOS by compiling and distributing it in a convenient, Debian-like format.
  • 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_69d8e51e7d948190aedbcd6c30361c39 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e658a2cc8481908d134b0b5cf79d06 completed April 20, 2026, 4:47 p.m.
Created at: April 10, 2026, 1:51 p.m.