Triple

T9630869
Position Surface form Disambiguated ID Type / Status
Subject FCSP E232798 entity
Predicate governingBody P46 FINISHED
Object DFB E57011 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: DFB | Statement: [FCSP, governingBody, DFB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DFB
Context triple: [FCSP, governingBody, DFB]
  • A. DFL
    DFL (Deutsche Fußball Liga) is the governing body responsible for operating and marketing Germany’s top professional football leagues.
  • B. SFB
    SFB is the FAA airport code for Orlando Sanford International Airport, a commercial airport serving the Orlando, Florida metropolitan area.
  • C. SFB
    SFB is the commonly used abbreviation for the San Francisco Ballet, one of the oldest and most prestigious professional ballet companies in the United States.
  • D. Western German Football Association
    The Western German Football Association is a regional governing body responsible for organizing and overseeing football competitions and administration in the western part of Germany.
  • E. German Football Association chosen
    The German Football Association is the national governing body responsible for overseeing football in Germany, including organizing leagues, competitions, and the national teams.
  • 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_69ca848940cc8190b97cec654cb3bb4a completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9b2621408190bfe2ea5a05359ee0 completed April 1, 2026, 10:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1822e12b8819089d4a64a9980cfcd completed April 4, 2026, 9:27 p.m.
Created at: March 30, 2026, 8:11 p.m.