Triple

T13405637
Position Surface form Disambiguated ID Type / Status
Subject Athenische Mitteilungen E319948 entity
Predicate abbreviation P43 FINISHED
Object AM
AM is the standard scholarly abbreviation for "Athenische Mitteilungen," a prominent German archaeological journal focused on research related to ancient Greece.
 E1038145 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: AM | Statement: [Athenische Mitteilungen, abbreviation, AM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AM
Context triple: [Athenische Mitteilungen, abbreviation, AM]
  • A. AM
    AM is the two-letter IATA airline designator used to identify Aeroméxico in global aviation systems.
  • B. AM
    AM is the two-letter ISO 3166 country code assigned to the Republic of Armenia.
  • C. AM
    AM is a radio broadcasting band used for transmitting audio signals via amplitude modulation, commonly for talk radio and news stations.
  • D. AM
    AM is the regional vehicle registration code used on license plates for the Greek administrative region of Eastern Macedonia and Thrace.
  • E. AM
    AM is a critically acclaimed 2013 studio album by English rock band Arctic Monkeys, known for its sleek blend of indie rock, R&B, and hip-hop influences.
  • 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: AM
Triple: [Athenische Mitteilungen, abbreviation, AM]
Generated description
AM is the standard scholarly abbreviation for "Athenische Mitteilungen," a prominent German archaeological journal focused on research related to ancient Greece.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AM
Target entity description: AM is the standard scholarly abbreviation for "Athenische Mitteilungen," a prominent German archaeological journal focused on research related to ancient Greece.
  • A. AM
    AM is a post-nominal title signifying appointment as a Member of the Order of Australia, an honor awarded for significant service to the nation or humanity.
  • B. AM
    AM is the regional vehicle registration code used on license plates for the Greek administrative region of Eastern Macedonia and Thrace.
  • C. AM
    AM is a radio broadcasting band used for transmitting audio signals via amplitude modulation, commonly for talk radio and news stations.
  • D. AM
    AM is the two-letter ISO 3166 country code assigned to the Republic of Armenia.
  • E. AM
    AM is the two-letter IATA airline designator used to identify Aeroméxico in global aviation systems.
  • 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_69d806b943cc8190b6af624d385d7e12 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbae4be498819094798473a1bfd853 completed April 12, 2026, 2:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7307904608190ad647f741c08dc42 completed May 3, 2026, 11:24 a.m.
NEDg Description generation batch_69f731d83ca081909ff0762c01280993 completed May 3, 2026, 11:30 a.m.
NED2 Entity disambiguation (via description) batch_69f7324625288190bed99890ba021e46 completed May 3, 2026, 11:32 a.m.
Created at: April 9, 2026, 9:34 p.m.