Triple

T4504484
Position Surface form Disambiguated ID Type / Status
Subject Canadian University Society for Intercollegiate Debate E101298 entity
Predicate abbreviation P43 FINISHED
Object CUSID
CUSID is a national organization that coordinates and promotes competitive university debating across Canada.
 E447429 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: CUSID | Statement: [Canadian University Society for Intercollegiate Debate, abbreviation, CUSID]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CUSID
Context triple: [Canadian University Society for Intercollegiate Debate, abbreviation, CUSID]
  • A. CID
    The CID was a high-level British government body responsible for coordinating defense and military policy across the Empire in the early 20th century.
  • B. CID
    CID is the abbreviated name for the Criminal Investigations Division of the Metropolitan Police Department, responsible for conducting in-depth investigations into serious crimes.
  • C. CU
    CU is the two-letter ISO 3166-1 alpha-2 country code assigned to Cuba.
  • D. CU
    CU is the common abbreviation for the Christian Union, a Christian student organization found at many universities.
  • E. CU
    CU is the common abbreviation for Chulalongkorn University, a leading public research university in Bangkok, Thailand.
  • 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: CUSID
Triple: [Canadian University Society for Intercollegiate Debate, abbreviation, CUSID]
Generated description
CUSID is a national organization that coordinates and promotes competitive university debating across Canada.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CUSID
Target entity description: CUSID is a national organization that coordinates and promotes competitive university debating across Canada.
  • A. CID
    The CID was a high-level British government body responsible for coordinating defense and military policy across the Empire in the early 20th century.
  • B. CID
    CID is the abbreviated name for the Criminal Investigations Division of the Metropolitan Police Department, responsible for conducting in-depth investigations into serious crimes.
  • C. CU
    CU is the two-letter ISO 3166-1 alpha-2 country code assigned to Cuba.
  • D. CU
    CU is the common abbreviation for the Christian Union, a Christian student organization found at many universities.
  • E. CU
    CU is the common abbreviation for Chulalongkorn University, a leading public research university in Bangkok, Thailand.
  • 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_69bd43d175248190894dc58b5b395c26 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd56fe17608190ae5dc27052b7c337 completed March 20, 2026, 2:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd6f958de0819082d17c165d25e703 completed March 20, 2026, 4:02 p.m.
NEDg Description generation batch_69bd71b00a2481909309765b6cc2e73d completed March 20, 2026, 4:11 p.m.
NED2 Entity disambiguation (via description) batch_69bd727abda08190bdc1d6ea015f3e46 completed March 20, 2026, 4:14 p.m.
Created at: March 20, 2026, 1:01 p.m.