Triple

T1773289
Position Surface form Disambiguated ID Type / Status
Subject Angiosperm Phylogeny Group E38921 entity
Predicate abbreviation P43 FINISHED
Object APG
APG is an internationally recognized collaborative group of botanists that develops and maintains a modern, phylogeny-based classification system for flowering plants.
 E201684 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: APG | Statement: [Angiosperm Phylogeny Group, abbreviation, APG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: APG
Context triple: [Angiosperm Phylogeny Group, abbreviation, APG]
  • A. Ap
    Ap is the commonly used abbreviation for the Norwegian Labour Party, a major social-democratic political party in Norway.
  • B. APRIN
    APRIN is a Japanese organization focused on promoting research integrity and ethical conduct in academic and scientific communities.
  • C. PAPPG
    PAPPG is the National Science Foundation’s comprehensive guide outlining the policies, procedures, and requirements for preparing and managing NSF grant proposals and awards.
  • D. AG
    AG is the standard abbreviation for the United States Attorney General, the chief law enforcement officer and head of the U.S. Department of Justice.
  • E. AG
    AG is the two-letter ISO 3166-1 alpha-2 country code assigned to Antigua and Barbuda.
  • 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: APG
Triple: [Angiosperm Phylogeny Group, abbreviation, APG]
Generated description
APG is an internationally recognized collaborative group of botanists that develops and maintains a modern, phylogeny-based classification system for flowering plants.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: APG
Target entity description: APG is an internationally recognized collaborative group of botanists that develops and maintains a modern, phylogeny-based classification system for flowering plants.
  • A. Ap
    Ap is the commonly used abbreviation for the Norwegian Labour Party, a major social-democratic political party in Norway.
  • B. APRIN
    APRIN is a Japanese organization focused on promoting research integrity and ethical conduct in academic and scientific communities.
  • C. PAPPG
    PAPPG is the National Science Foundation’s comprehensive guide outlining the policies, procedures, and requirements for preparing and managing NSF grant proposals and awards.
  • D. AG
    AG is the standard abbreviation for the United States Attorney General, the chief law enforcement officer and head of the U.S. Department of Justice.
  • E. AG
    AG is the two-letter ISO 3166-1 alpha-2 country code assigned to Antigua and Barbuda.
  • 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_69a8862e61708190af97b9838cc3f5de completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa64b59428819082e0d43a61f4f299 completed March 6, 2026, 5:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69adb5c96694819085f3ccafb141802f completed March 8, 2026, 5:45 p.m.
NEDg Description generation batch_69adb8b3c0a48190bf5f3a32d8862c54 completed March 8, 2026, 5:58 p.m.
NED2 Entity disambiguation (via description) batch_69adb97b8c8081909a806d16efd5882b completed March 8, 2026, 6:01 p.m.
Created at: March 4, 2026, 7:31 p.m.