Triple

T21486308
Position Surface form Disambiguated ID Type / Status
Subject Bangladesh Premier League E530124 entity
Predicate shortName P43 FINISHED
Object BPL
BPL is a professional Twenty20 cricket league in Bangladesh featuring franchise teams competing in a fast-paced tournament format.
 E1488093 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: BPL | Statement: [Bangladesh Premier League, shortName, BPL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BPL
Context triple: [Bangladesh Premier League, shortName, BPL]
  • A. BPL
    BPL is the station code for Bayerischer Platz, a Berlin U-Bahn station in Germany.
  • B. BUPL
    BUPL is a Danish trade union representing early childhood educators and pedagogical staff.
  • C. BVL
    BVL is Germany’s Federal Office of Consumer Protection and Food Safety, the national authority responsible for ensuring food safety and protecting consumer health.
  • D. BPC
    BPC is the commonly used abbreviation for the Bryant Park Corporation, the nonprofit organization that manages and maintains Bryant Park in New York City.
  • E. BL
    BL is the vehicle registration code used for the city of Banja Luka in Bosnia and Herzegovina.
  • 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: BPL
Triple: [Bangladesh Premier League, shortName, BPL]
Generated description
BPL is a professional Twenty20 cricket league in Bangladesh featuring franchise teams competing in a fast-paced tournament format.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BPL
Target entity description: BPL is a professional Twenty20 cricket league in Bangladesh featuring franchise teams competing in a fast-paced tournament format.
  • A. BPL
    BPL is the station code for Bayerischer Platz, a Berlin U-Bahn station in Germany.
  • B. BUPL
    BUPL is a Danish trade union representing early childhood educators and pedagogical staff.
  • C. BVL
    BVL is Germany’s Federal Office of Consumer Protection and Food Safety, the national authority responsible for ensuring food safety and protecting consumer health.
  • D. BPC
    BPC is the commonly used abbreviation for the Bryant Park Corporation, the nonprofit organization that manages and maintains Bryant Park in New York City.
  • E. BL
    BL is the vehicle registration code used for the city of Banja Luka in Bosnia and Herzegovina.
  • 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_69e0c45acc3881908e38d3f28964152b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea370adc8190b79fe26e2eba1dca completed April 23, 2026, 9:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09e1339bbc81908aa0c398a0c106a4 completed May 17, 2026, 3:39 p.m.
NEDg Description generation batch_6a09e2913c748190b6a14cc336cf843c completed May 17, 2026, 3:45 p.m.
NED2 Entity disambiguation (via description) batch_6a09e2fce69c81909d038daa7334d4a7 completed May 17, 2026, 3:47 p.m.
Created at: April 16, 2026, 6:22 p.m.