Triple

T16587931
Position Surface form Disambiguated ID Type / Status
Subject Leopold Ružička E403006 entity
Predicate employer P7 FINISHED
Object Ciba E584144 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: Ciba | Statement: [Leopold Ružička, employer, Ciba]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ciba
Context triple: [Leopold Ružička, employer, Ciba]
  • A. Ciba-Geigy chosen
    Ciba-Geigy was a major Swiss pharmaceutical and chemical company that became one of the predecessors of Novartis after its merger with Sandoz in 1996.
  • B. Bayer
    Bayer is a major German multinational pharmaceutical and life sciences company known for products such as aspirin and its work in healthcare and agriculture.
  • C. Syntex
    Syntex was a pioneering pharmaceutical company best known for its role in developing the first oral contraceptive pill and advancing steroid chemistry.
  • D. Hoechst
    Hoechst was a major German chemical and pharmaceutical company that later became part of the conglomerate IG Farben.
  • E. Dalmine
    Dalmine is an industrial town in northern Italy known for its steel production and manufacturing activities.
  • 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_69d88387363c8190a97a0c942130de97 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3599daa508190a9ed6f64138c0e53 completed April 18, 2026, 10:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a007599dcd4819089bbd0569b3d9a12 completed May 10, 2026, 12:10 p.m.
Created at: April 10, 2026, 5:16 a.m.