Triple

T5822632
Position Surface form Disambiguated ID Type / Status
Subject FF UK E129146 entity
Predicate shortName P43 FINISHED
Object FF UK E129146 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: FF UK | Statement: [FF UK, shortName, FF UK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FF UK
Context triple: [FF UK, shortName, FF UK]
  • A. FF UK chosen
    FF UK is the Faculty of Arts at Charles University in Prague, one of the oldest and largest humanities and social sciences faculties in Central Europe.
  • B. CAF UK
    CAF UK is the United Kingdom-based subsidiary of the Spanish rolling stock manufacturer CAF, responsible for supplying and maintaining trains and rail solutions in the UK market.
  • C. FFK
    FFK is the football association responsible for organizing and overseeing the national football activities and competitions in Curaçao.
  • D. UKFF
    UKFF is the ICAO airport code assigned to Simferopol International Airport in Crimea.
  • E. UK
    UK is the stock ticker symbol for Union Carbide Corporation, a major American chemical and polymers company historically known for its industrial products and the Bhopal disaster.
  • 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_69c0084869e881908d7859492183ca7b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0341715bc81909568b00ccc79869d completed March 22, 2026, 6:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0985ab01c8190ac03cb95427c688d completed March 23, 2026, 1:33 a.m.
Created at: March 22, 2026, 3:53 p.m.