Triple

T6311236
Position Surface form Disambiguated ID Type / Status
Subject Novartis E141505 entity
Predicate location P40 FINISHED
Object Basel E22322 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: Basel | Statement: [Novartis, location, Basel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Basel
Context triple: [Novartis, location, Basel]
  • A. Basel-Stadt chosen
    Basel-Stadt is a small, urban Swiss canton centered on the city of Basel, a major cultural and economic hub in northwestern Switzerland.
  • B. Zurich
    Zurich is the largest city in Switzerland, known as a global financial hub and cultural center situated on the shores of Lake Zurich.
  • C. Berne
    Berne is the de facto capital city of Switzerland and the seat of its federal government institutions.
  • D. Stettlen
    Stettlen is a municipality in the canton of Bern in Switzerland, situated just east of the city of Bern and functioning largely as a residential and commuter community.
  • E. St. Gallen
    St. Gallen is a historic city in northeastern Switzerland renowned for its UNESCO-listed Abbey of Saint Gall and rich textile heritage.
  • 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_69c008d00efc8190a36c05b4b4a3bf4b completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0649d1e048190a3fc7fbce9d2ee57 completed March 22, 2026, 9:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83c2fa16c8190b03ed4d47b6090e7 completed March 28, 2026, 8:38 p.m.
Created at: March 22, 2026, 4:28 p.m.