Triple

T13025585
Position Surface form Disambiguated ID Type / Status
Subject Cold Bay, Alaska E326296 entity
Predicate IATAAirportCode P418 FINISHED
Object CDB
CDB is the IATA airport code for the regional airport serving Cold Bay in the Aleutian region of Alaska.
E1016225 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: CDB | Statement: [Cold Bay, Alaska, IATAAirportCode, CDB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CDB
Context triple: [Cold Bay, Alaska, IATAAirportCode, CDB]
  • A. CDB
    CDB is a regional multilateral development bank that provides financial and technical assistance to promote economic and social development in the Caribbean.
  • B. CDB
    CDB is the National Rail station code for Cardiff Bay railway station in Cardiff, Wales.
  • C. CDB
    CDB is the commonly used abbreviation for China Development Bank, a major Chinese policy bank that provides medium- to long-term financing for national infrastructure and development projects.
  • D. BDB
    BDB is the IATA airport code for Bundaberg Airport, a regional airport serving the city of Bundaberg in Queensland, Australia.
  • E. SDB
    SDB is the post-nominal abbreviation used by members of the Salesians of Don Bosco, a Roman Catholic religious institute dedicated especially to the education and evangelization of youth.
  • 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: CDB
Triple: [Cold Bay, Alaska, IATAAirportCode, CDB]
Generated description
CDB is the IATA airport code for the regional airport serving Cold Bay in the Aleutian region of Alaska.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CDB
Target entity description: CDB is the IATA airport code for the regional airport serving Cold Bay in the Aleutian region of Alaska.
  • A. CDB
    CDB is a regional multilateral development bank that provides financial and technical assistance to promote economic and social development in the Caribbean.
  • B. CDB
    CDB is the National Rail station code for Cardiff Bay railway station in Cardiff, Wales.
  • C. CDB
    CDB is the commonly used abbreviation for China Development Bank, a major Chinese policy bank that provides medium- to long-term financing for national infrastructure and development projects.
  • D. BDB
    BDB is the IATA airport code for Bundaberg Airport, a regional airport serving the city of Bundaberg in Queensland, Australia.
  • E. SDB
    SDB is the post-nominal abbreviation used by members of the Salesians of Don Bosco, a Roman Catholic religious institute dedicated especially to the education and evangelization of youth.
  • 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_69d8076cc45c81908123123f43e69266 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97efac71881908a21d70c3c6ce099 completed April 10, 2026, 10:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6c11f83d88190bc153dba75db0995 completed May 3, 2026, 3:29 a.m.
NEDg Description generation batch_69f6c43bc75c8190887b8135fbc8bbb5 completed May 3, 2026, 3:42 a.m.
NED2 Entity disambiguation (via description) batch_69f6c50cf3c08190b1ef6379f1f96201 completed May 3, 2026, 3:46 a.m.
Created at: April 9, 2026, 8:53 p.m.