Triple

T23554003
Position Surface form Disambiguated ID Type / Status
Subject Berlin C E578128 entity
Predicate fareZoneCombination P80296 FINISHED
Object BC
BC is a public transport fare zone combination in Berlin that covers both the B and C tariff areas but excludes the central A zone.
 E1590130 NE FINISHED

How this triple was built (4 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: BC | Statement: [Berlin C, fareZoneCombination, BC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BC
Context triple: [Berlin C, fareZoneCombination, BC]
  • A. BC
    BC is the IATA airline designator assigned to Skymark Airlines, a Japanese low-cost carrier.
  • B. BC
    BC is the Business Constituency, a group within the ICANN community that represents the interests of commercial Internet users in domain name policy development.
  • C. BC
    BC is a private Jesuit research university located in Chestnut Hill, Massachusetts, known for its strong liberal arts programs and competitive NCAA Division I athletics.
  • D. BC
    BC is the Canadian province of British Columbia, located on the west coast of Canada with Vancouver as its largest city.
  • E. BC
    BC is the vehicle registration code for Bacău County in Romania.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: BC
Triple: [Berlin C, fareZoneCombination, BC]
Generated description
BC is a public transport fare zone combination in Berlin that covers both the B and C tariff areas but excludes the central A zone.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BC
Target entity description: BC is a public transport fare zone combination in Berlin that covers both the B and C tariff areas but excludes the central A zone.
  • A. BC
    BC is the IATA airline designator assigned to Skymark Airlines, a Japanese low-cost carrier.
  • B. BC
    BC is the vehicle registration code for Bacău County in Romania.
  • C. BC
    BC is the Business Constituency, a group within the ICANN community that represents the interests of commercial Internet users in domain name policy development.
  • D. BC
    BC is the commonly used abbreviation for Bakersfield College, a public community college located in Bakersfield, California.
  • E. BC
    BC is the commonly used abbreviation for Brooklyn College, a senior college of the City University of New York located in Brooklyn.
  • F. None of above. chosen

Provenance (5 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_69e245fa93448190919cb04534560542 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1aed17fc881908b45dcde14790d42 completed April 29, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0cdf67efbc8190a75c1d6cb9bd63f9 completed May 19, 2026, 10:08 p.m.
NEDg Description generation batch_6a0ce12579188190befd636d3714675a completed May 19, 2026, 10:16 p.m.
NED2 Entity disambiguation (via description) batch_6a0ce187efa48190876f67fef4873af2 completed May 19, 2026, 10:17 p.m.
Created at: April 17, 2026, 6:12 p.m.