Triple

T4332935
Position Surface form Disambiguated ID Type / Status
Subject Swiss Academy of Medical Sciences E97395 entity
Predicate abbreviation P43 FINISHED
Object ASSM
ASSM is the abbreviation for the Swiss Academy of Medical Sciences, a leading Swiss institution that promotes medical research, ethics, and healthcare policy.
 E431182 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: ASSM | Statement: [Swiss Academy of Medical Sciences, abbreviation, ASSM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ASSM
Context triple: [Swiss Academy of Medical Sciences, abbreviation, ASSM]
  • A. ASM
    ASM is the three-letter ISO 3166-1 alpha-3 country code assigned to American Samoa, an unincorporated territory of the United States in the South Pacific Ocean.
  • B. ASM
    ASM is a leading professional organization dedicated to advancing the microbial sciences through research, education, and advocacy.
  • C. OASAM
    OASAM is a division of the U.S. Department of Labor responsible for providing administrative, management, and support services across the department.
  • D. AAS
    AAS is a federal acquisition organization that provides assisted procurement and contracting services to U.S. government agencies.
  • E. AAS
    AAS is a major professional organization dedicated to the advancement of astronomy and related sciences in the United States.
  • 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: ASSM
Triple: [Swiss Academy of Medical Sciences, abbreviation, ASSM]
Generated description
ASSM is the abbreviation for the Swiss Academy of Medical Sciences, a leading Swiss institution that promotes medical research, ethics, and healthcare policy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ASSM
Target entity description: ASSM is the abbreviation for the Swiss Academy of Medical Sciences, a leading Swiss institution that promotes medical research, ethics, and healthcare policy.
  • A. ASM
    ASM is the three-letter ISO 3166-1 alpha-3 country code assigned to American Samoa, an unincorporated territory of the United States in the South Pacific Ocean.
  • B. ASM
    ASM is a leading professional organization dedicated to advancing the microbial sciences through research, education, and advocacy.
  • C. OASAM
    OASAM is a division of the U.S. Department of Labor responsible for providing administrative, management, and support services across the department.
  • D. AAS
    AAS is a federal acquisition organization that provides assisted procurement and contracting services to U.S. government agencies.
  • E. AAS
    AAS is a major professional organization dedicated to the advancement of astronomy and related sciences in the United States.
  • 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_69b3454662a481908fbcd0bbfaa3a0a4 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3514faaac819081475681fd10da24 completed March 12, 2026, 11:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5d0a307388190af4cb98b03e9656d completed March 14, 2026, 9:18 p.m.
NEDg Description generation batch_69b5d12a54e0819081379fd1ee85914b completed March 14, 2026, 9:20 p.m.
NED2 Entity disambiguation (via description) batch_69b5d194975481908b029ab106223c6c completed March 14, 2026, 9:22 p.m.
Created at: March 12, 2026, 11:13 p.m.