Triple

T14156421
Position Surface form Disambiguated ID Type / Status
Subject Neubau E350824 entity
Predicate locatedIn P40 FINISHED
Object St. Alban-Graben E350828 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: St. Alban-Graben | Statement: [Neubau, locatedIn, St. Alban-Graben]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: St. Alban-Graben
Context triple: [Neubau, locatedIn, St. Alban-Graben]
  • A. St. Alban-Graben chosen
    St. Alban-Graben is a central street in Basel, Switzerland, known for hosting major cultural institutions and serving as an important urban thoroughfare.
  • B. Schwarzer Graben
    Schwarzer Graben is a small waterway or channel in Germany located near the river island of Hasselwerder.
  • C. Kreuzlinger Forstgraben
    Kreuzlinger Forstgraben is a small watercourse in Bavaria that serves as one of the tributary streams feeding into Lake Starnberg.
  • D. Kleiner Grasbrook
    Kleiner Grasbrook is a district of Hamburg, Germany, located in the central borough of Hamburg-Mitte and characterized by its port-related and waterfront areas along the Elbe River.
  • E. Mühlengraben
    Mühlengraben is a small watercourse in the town of Gifhorn in Lower Saxony, Germany, likely serving as a mill stream or side channel of a larger river.
  • 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_69d8278775fc8190b0802d22ca2f495d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6135744c81909a43d659f5fe2895 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7ec6448819087e50aac964ec637 completed May 7, 2026, 8:37 p.m.
Created at: April 10, 2026, 12:58 a.m.