Triple

T8489805
Position Surface form Disambiguated ID Type / Status
Subject ICANN At-Large Community E200938 entity
Predicate usesAcronym P43 FINISHED
Object At-Large
At-Large is the global community of individual Internet users who participate in ICANN’s policy development and decision-making processes.
E737310 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: At-Large | Statement: [ICANN At-Large Community, usesAcronym, At-Large]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: At-Large
Context triple: [ICANN At-Large Community, usesAcronym, At-Large]
  • A. Yost
    Yost is a surname most notably associated with Fielding H. Yost, the pioneering early 20th-century American college football coach.
  • B. Arpoador
    Arpoador is a famous rocky peninsula and beach area in Rio de Janeiro, Brazil, renowned for its surfing waves and sunset views over the ocean.
  • C. Anthemous
    Anthemous was an ancient region of Macedonia located adjacent to Bottiaea, known from classical Greek geography and history.
  • D. Arcop
    Arcop was a prominent Canadian architectural firm known for its modernist designs and major cultural and institutional projects across Canada.
  • E. Fadden
    Fadden is an Australian federal electoral division in Queensland, represented in the House of Representatives.
  • 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: At-Large
Triple: [ICANN At-Large Community, usesAcronym, At-Large]
Generated description
At-Large is the global community of individual Internet users who participate in ICANN’s policy development and decision-making processes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: At-Large
Target entity description: At-Large is the global community of individual Internet users who participate in ICANN’s policy development and decision-making processes.
  • A. Yost
    Yost is a surname most notably associated with Fielding H. Yost, the pioneering early 20th-century American college football coach.
  • B. Arpoador
    Arpoador is a famous rocky peninsula and beach area in Rio de Janeiro, Brazil, renowned for its surfing waves and sunset views over the ocean.
  • C. Anthemous
    Anthemous was an ancient region of Macedonia located adjacent to Bottiaea, known from classical Greek geography and history.
  • D. Arcop
    Arcop was a prominent Canadian architectural firm known for its modernist designs and major cultural and institutional projects across Canada.
  • E. Fadden
    Fadden is an Australian federal electoral division in Queensland, represented in the House of Representatives.
  • 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_69ca831d7b148190a6e32c1de43ab13b completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe5596f1c8190aead21a245f21c07 completed March 31, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce3a4e5be48190b5c598123ef75f8b completed April 2, 2026, 9:43 a.m.
NEDg Description generation batch_69ce3d0323248190a076a209df98c96c completed April 2, 2026, 9:55 a.m.
NED2 Entity disambiguation (via description) batch_69ce3d7909f48190a46f58fca75d7740 completed April 2, 2026, 9:57 a.m.
Created at: March 30, 2026, 6:13 p.m.