Triple

T3181127
Position Surface form Disambiguated ID Type / Status
Subject Isar E66587 entity
Predicate nearbyCity P350 FINISHED
Object Innsbruck E110788 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: Innsbruck | Statement: [Isar, nearbyCity, Innsbruck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Innsbruck
Context triple: [Isar, nearbyCity, Innsbruck]
  • A. Innsbruck chosen
    Innsbruck is a city in western Austria known for its Alpine setting and winter sports facilities, and it later successfully hosted the Winter Olympics in 1964 and 1976.
  • B. Salzburg
    Salzburg is a historic Austrian city on the Salzach River, renowned for its baroque architecture, Alpine setting, and as the birthplace of composer Wolfgang Amadeus Mozart.
  • C. Kufstein
    Kufstein is a historic town in the Austrian state of Tyrol, known for its medieval fortress and picturesque setting in the Alps near the German border.
  • D. Klagenfurt
    Klagenfurt is the capital city of the Austrian state of Carinthia, known for its historic old town and proximity to Lake Wörthersee.
  • E. Linz
    Linz is a major Austrian city known for its industrial heritage, vibrant cultural scene, and location along the Danube 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_69ad8586a34c8190944c63ec11a8de1a completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada6a1280c8190b59a2afd30312c02 completed March 8, 2026, 4:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69b31a6206988190a6aaecbfe8ccf0bf completed March 12, 2026, 7:56 p.m.
Created at: March 8, 2026, 3:06 p.m.