Triple

T22963444
Position Surface form Disambiguated ID Type / Status
Subject EFA E570968 entity
Predicate affiliation P10 FINISHED
Object COA
COA is an organization or institution with which the EFA (likely a group, association, or federation) is formally affiliated.
 E1317414 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: COA | Statement: [EFA, affiliation, COA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: COA
Context triple: [EFA, affiliation, COA]
  • A. COA
    COA is the acronym for the Commission on Audit, the independent constitutional body in the Philippines responsible for auditing government funds and properties.
  • B. COA
    COA is the ICAO airline designator formerly used by Continental Airlines, a major U.S. carrier that merged with United Airlines.
  • C. COA
    COA is the abbreviation for Taiwan’s Council of Agriculture, the central government agency responsible for agricultural, forestry, fishery, and animal husbandry policies.
  • D. COA
    COA is the Dutch national agency responsible for managing reception and accommodation for asylum seekers in the Netherlands.
  • E. CoA+A
    CoA+A is the commonly used abbreviation for the College of Arts + Architecture, an academic unit focused on disciplines such as visual arts, design, and performance.
  • 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: COA
Triple: [EFA, affiliation, COA]
Generated description
COA is an organization or institution with which the EFA (likely a group, association, or federation) is formally affiliated.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: COA
Target entity description: COA is an organization or institution with which the EFA (likely a group, association, or federation) is formally affiliated.
  • A. COA
    COA is the acronym for the Commission on Audit, the independent constitutional body in the Philippines responsible for auditing government funds and properties.
  • B. COA
    COA is the ICAO airline designator formerly used by Continental Airlines, a major U.S. carrier that merged with United Airlines.
  • C. COA
    COA is the abbreviation for Taiwan’s Council of Agriculture, the central government agency responsible for agricultural, forestry, fishery, and animal husbandry policies.
  • D. COA chosen
    COA is the Dutch national agency responsible for managing reception and accommodation for asylum seekers in the Netherlands.
  • E. CoA+A
    CoA+A is the commonly used abbreviation for the College of Arts + Architecture, an academic unit focused on disciplines such as visual arts, design, and performance.
  • F. None of above.

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_69e245b212a88190b5259caf51606084 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f181f66fbc8190a4a7b73d17537132 completed April 29, 2026, 3:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bca22caa88190889e965c78477a96 completed May 19, 2026, 2:25 a.m.
NEDg Description generation batch_6a0bcb1904c88190ac32e5709bc95858 completed May 19, 2026, 2:29 a.m.
NED2 Entity disambiguation (via description) batch_6a0bcbb8793881909621b16c9ad51cbb completed May 19, 2026, 2:32 a.m.
Created at: April 17, 2026, 3:47 p.m.