Triple

T23153554
Position Surface form Disambiguated ID Type / Status
Subject AFI E578381 entity
Predicate acronym P43 FINISHED
Object AFI NE NERFINISHED

How this triple was built (2 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: AFI | Statement: [AFI, acronym, AFI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AFI
Context triple: [AFI, acronym, AFI]
  • A. AFI
    AFI (Australian Film Institute) is a national organization that promotes and recognizes excellence in Australian film and television through awards, advocacy, and industry support.
  • B. AFI
    AFI is an American rock band known for evolving from hardcore punk roots into a more melodic, gothic-tinged alternative sound and achieving mainstream success in the 2000s.
  • C. AFI
    AFI is a global network of financial policymakers and regulators dedicated to advancing financial inclusion in developing and emerging economies.
  • D. AAFI
    AAFI refers to the Allied Air Forces in Italy, the combined air command of Allied nations operating in the Italian theater during World War II.
  • E. AFI Catalog of Feature Films
    AFI Catalog of Feature Films is a comprehensive, authoritative database documenting the production and release details of American feature-length motion pictures.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

Provenance (2 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_69e245fb8de081908f0eba7b5fd75bc4 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18efbe9a08190bcb6e822b8eab544 completed April 29, 2026, 4:54 a.m.
Created at: April 17, 2026, 4:01 p.m.