Triple

T16785380
Position Surface form Disambiguated ID Type / Status
Subject Otto Harbach E407956 entity
Predicate collaboratedWith P435 FINISHED
Object Emmerich Kálmán E575284 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: Emmerich Kálmán | Statement: [Otto Harbach, collaboratedWith, Emmerich Kálmán]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emmerich Kálmán
Context triple: [Otto Harbach, collaboratedWith, Emmerich Kálmán]
  • A. Emmerich Kálmán chosen
    Emmerich Kálmán was a prominent early 20th-century Hungarian composer best known for his popular operettas that blended Viennese waltz traditions with Hungarian folk influences.
  • B. Arthur Seidl
    Arthur Seidl was a German writer and theater critic associated with late 19th-century cultural and philosophical circles.
  • C. Klaus von Dohnanyi
    Klaus von Dohnanyi is a German politician and lawyer best known for serving as the First Mayor of Hamburg in the 1980s.
  • D. Hans Brunhart
    Hans Brunhart is a Liechtenstein politician who served for many years as the country's Prime Minister during the reign of Prince Hans-Adam II.
  • E. Zoltan Korda
    Zoltan Korda was a Hungarian-born British film director and producer known for his adventure and war films, often collaborating with his brothers in the London Films studio.
  • 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_69d8839270588190886720d9519bbf8f completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b21996cc81909deb88545af7079f completed April 18, 2026, 4:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00ab07bdcc819086479178e5b8b679 completed May 10, 2026, 3:57 p.m.
Created at: April 10, 2026, 5:22 a.m.