Triple

T14229406
Position Surface form Disambiguated ID Type / Status
Subject dba (Deutsche BA) E352711 entity
Predicate formerName P65 FINISHED
Object Deutsche BA E352711 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: Deutsche BA | Statement: [dba (Deutsche BA), formerName, Deutsche BA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deutsche BA
Context triple: [dba (Deutsche BA), formerName, Deutsche BA]
  • A. DE-BY
    DE-BY is the ISO 3166-2 regional code for the German federal state of Bavaria.
  • B. dba (Deutsche BA) chosen
    dba (Deutsche BA) was a German regional airline that operated domestic and European flights before being integrated into Air Berlin.
  • C. Saksa
    Saksa is a prominent mountain in Norway’s Sunnmøre Alps, known for its steep ascent and panoramic views over the Hjørundfjord.
  • D. Baier
    Baier is a surname most prominently associated with Bret Baier, the American television news anchor and host on Fox News.
  • E. Rentenmark
    The Rentenmark was a temporary German currency introduced in 1923 to halt hyperinflation and stabilize the economy during the Weimar Republic.
  • 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_69d8278adc7c8190a9218d69bce3c4e6 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de622b89fc8190af08dab9e1976759 completed April 14, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd2819bfec8190b555632338c53740 completed May 8, 2026, 12:02 a.m.
Created at: April 10, 2026, 1:07 a.m.