Triple

T19905551
Position Surface form Disambiguated ID Type / Status
Subject SC Bern E478404 entity
Predicate shortName P43 FINISHED
Object SCB
SCB is the commonly used abbreviation for SC Bern, a professional ice hockey club based in Bern, Switzerland.
E1400802 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: SCB | Statement: [SC Bern, shortName, SCB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SCB
Context triple: [SC Bern, shortName, SCB]
  • A. SCB
    SCB is the national statistical agency of Sweden responsible for producing official statistics and data for government, researchers, and the public.
  • B. SCB
    SCB was a 19th-century Swiss railway company that played a key role in developing the country’s early rail network.
  • C. SCBC
    SCBC is the rowing club of Selwyn College at the University of Cambridge, competing in college and university rowing events.
  • D. SCB-27
    SCB-27 was a major U.S. Navy post–World War II modernization program that extensively rebuilt Essex-class aircraft carriers to operate heavier, faster jet aircraft.
  • E. SBCG
    SBCG is the ICAO airport code for Campo Grande Air Base, a Brazilian Air Force installation located in Campo Grande, Brazil.
  • 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: SCB
Triple: [SC Bern, shortName, SCB]
Generated description
SCB is the commonly used abbreviation for SC Bern, a professional ice hockey club based in Bern, Switzerland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SCB
Target entity description: SCB is the commonly used abbreviation for SC Bern, a professional ice hockey club based in Bern, Switzerland.
  • A. SCB
    SCB was a 19th-century Swiss railway company that played a key role in developing the country’s early rail network.
  • B. SCB
    SCB is the national statistical agency of Sweden responsible for producing official statistics and data for government, researchers, and the public.
  • C. SCBC
    SCBC is the rowing club of Selwyn College at the University of Cambridge, competing in college and university rowing events.
  • D. SCB-27
    SCB-27 was a major U.S. Navy post–World War II modernization program that extensively rebuilt Essex-class aircraft carriers to operate heavier, faster jet aircraft.
  • E. SBCG
    SBCG is the ICAO airport code for Campo Grande Air Base, a Brazilian Air Force installation located in Campo Grande, Brazil.
  • 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_69d8e520682081909892916424699bd5 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65946916881909c3f52208c07aa64 completed April 20, 2026, 4:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07ea494af08190ac8c43797bff5012 completed May 16, 2026, 3:53 a.m.
NEDg Description generation batch_6a07ee6d8ef481908987eef826425806 completed May 16, 2026, 4:11 a.m.
NED2 Entity disambiguation (via description) batch_6a07eec5b4788190b697a0b7382b5c2b completed May 16, 2026, 4:12 a.m.
Created at: April 10, 2026, 1:52 p.m.