Triple

T617507
Position Surface form Disambiguated ID Type / Status
Subject Aeronautica Militare E14438 entity
Predicate shortName P43 FINISHED
Object AMI
AMI is the abbreviation commonly used for the Italian Air Force, the air and space warfare branch of Italy’s armed forces.
 E77499 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: AMI | Statement: [Aeronautica Militare, shortName, AMI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AMI
Context triple: [Aeronautica Militare, shortName, AMI]
  • A. AMA
    AMA is the leading professional association and lobbying group representing physicians and medical students in the United States.
  • B. AMM
    AMM is the commonly used abbreviation for the APEC Ministerial Meeting, the annual gathering of Asia-Pacific Economic Cooperation foreign and trade ministers.
  • C. AMS
    AMS is the three-letter IATA airport code for Amsterdam Airport Schiphol, the main international airport of the Netherlands.
  • D. ACE
    ACE (Altamont Corridor Express) is a commuter rail service in California’s San Joaquin Valley and East Bay that provides weekday trains between Stockton and San Jose.
  • E. ASA
    ASA is the commonly used abbreviation for the Acoustical Society of America, a leading scientific society dedicated to the study and advancement of acoustics.
  • 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: AMI
Triple: [Aeronautica Militare, shortName, AMI]
Generated description
AMI is the abbreviation commonly used for the Italian Air Force, the air and space warfare branch of Italy’s armed forces.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AMI
Target entity description: AMI is the abbreviation commonly used for the Italian Air Force, the air and space warfare branch of Italy’s armed forces.
  • A. AMA
    AMA is the leading professional association and lobbying group representing physicians and medical students in the United States.
  • B. AMM
    AMM is the commonly used abbreviation for the APEC Ministerial Meeting, the annual gathering of Asia-Pacific Economic Cooperation foreign and trade ministers.
  • C. AMS
    AMS is the three-letter IATA airport code for Amsterdam Airport Schiphol, the main international airport of the Netherlands.
  • D. ACE
    ACE (Altamont Corridor Express) is a commuter rail service in California’s San Joaquin Valley and East Bay that provides weekday trains between Stockton and San Jose.
  • E. ASA
    ASA is the commonly used abbreviation for the Acoustical Society of America, a leading scientific society dedicated to the study and advancement of acoustics.
  • 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_69a4934b17c881909ace8270e8ddd202 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49e2418c881908552d2c4a5006e97 completed March 1, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69a55a77b6648190a2d07471442b401a completed March 2, 2026, 9:37 a.m.
NEDg Description generation batch_69a55b80320c8190a4e9eba92cd2839a completed March 2, 2026, 9:42 a.m.
NED2 Entity disambiguation (via description) batch_69a55bcfce508190b58e0289775125f9 completed March 2, 2026, 9:43 a.m.
Created at: March 1, 2026, 7:35 p.m.