Triple

T17561964
Position Surface form Disambiguated ID Type / Status
Subject Paraguayan Air Force E427712 entity
Predicate abbreviation P43 FINISHED
Object FAP
FAP is the acronym commonly used for the Paraguayan Air Force, the aerial warfare branch of Paraguay’s armed forces.
 E1275635 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: FAP | Statement: [Paraguayan Air Force, abbreviation, FAP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FAP
Context triple: [Paraguayan Air Force, abbreviation, FAP]
  • A. FAP
    FAP is the acronym for the Peruvian Air Force, the aerial warfare branch of Peru’s armed forces.
  • B. FAP
    FAP is the acronym for the Portuguese Air Force, the aerial warfare branch of Portugal’s Armed Forces.
  • C. FAPS
    FAPS is a professional honorific title signifying election as a Fellow of the American Physical Society in recognition of exceptional contributions to physics.
  • D. FPA
    FPA is the Finnish acronym for the Social Insurance Institution of Finland, the national agency responsible for administering Finland’s social security benefits.
  • E. FAS
    FAS is a U.S.-based nonprofit policy and research organization focused on science, technology, national security, and public policy issues.
  • 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: FAP
Triple: [Paraguayan Air Force, abbreviation, FAP]
Generated description
FAP is the acronym commonly used for the Paraguayan Air Force, the aerial warfare branch of Paraguay’s armed forces.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FAP
Target entity description: FAP is the acronym commonly used for the Paraguayan Air Force, the aerial warfare branch of Paraguay’s armed forces.
  • A. FAP
    FAP is the acronym for the Peruvian Air Force, the aerial warfare branch of Peru’s armed forces.
  • B. FAP
    FAP is the acronym for the Portuguese Air Force, the aerial warfare branch of Portugal’s Armed Forces.
  • C. FAPS
    FAPS is a professional honorific title signifying election as a Fellow of the American Physical Society in recognition of exceptional contributions to physics.
  • D. FPA
    FPA is the Finnish acronym for the Social Insurance Institution of Finland, the national agency responsible for administering Finland’s social security benefits.
  • E. FAS
    FAS is the commonly used abbreviation for the Faculty of Applied Sciences, an academic division focused on practical and technical scientific disciplines.
  • 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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e456274c888190ac80402e391674dd completed April 19, 2026, 4:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01d29694a8819095351b929cfaf324 completed May 11, 2026, 12:59 p.m.
NEDg Description generation batch_6a01d4436b448190bff8710eac0ce569 completed May 11, 2026, 1:06 p.m.
NED2 Entity disambiguation (via description) batch_6a01d49cb9c081908b07b87ec3b2a133 completed May 11, 2026, 1:07 p.m.
Created at: April 10, 2026, 5:50 a.m.