Triple

T7238109
Position Surface form Disambiguated ID Type / Status
Subject Ko Samui E155281 entity
Predicate airportIATAcode P418 FINISHED
Object USM
USM is the IATA airport code for Samui International Airport serving Ko Samui in Thailand.
 E652230 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: USM | Statement: [Ko Samui, airportIATAcode, USM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: USM
Context triple: [Ko Samui, airportIATAcode, USM]
  • A. USM
    USM (User-based Security Model) is the SNMPv3 security framework that provides user-level authentication, privacy (encryption), and access control for Simple Network Management Protocol communications.
  • B. USM
    USM is the commonly used abbreviation for the Federico Santa María Technical University, a prominent Chilean institution known for its strong engineering and science programs.
  • C. USM
    USM is the stock ticker symbol for United States Cellular Corporation, a regional wireless telecommunications provider in the United States.
  • D. USM
    USM is a public research university located in Hattiesburg, Mississippi, known for its programs in the arts, sciences, and education.
  • E. USM
    USM is the abbreviation for the U.S. Department of State’s Under Secretary for Management, the senior official overseeing the department’s administrative, budgetary, and logistical functions.
  • 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: USM
Triple: [Ko Samui, airportIATAcode, USM]
Generated description
USM is the IATA airport code for Samui International Airport serving Ko Samui in Thailand.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: USM
Target entity description: USM is the IATA airport code for Samui International Airport serving Ko Samui in Thailand.
  • A. USM
    USM (User-based Security Model) is the SNMPv3 security framework that provides user-level authentication, privacy (encryption), and access control for Simple Network Management Protocol communications.
  • B. USM
    USM is the commonly used abbreviation for the Federico Santa María Technical University, a prominent Chilean institution known for its strong engineering and science programs.
  • C. USM
    USM is the stock ticker symbol for United States Cellular Corporation, a regional wireless telecommunications provider in the United States.
  • D. USM
    USM is a public research university located in Hattiesburg, Mississippi, known for its programs in the arts, sciences, and education.
  • E. USM
    USM is the abbreviation for the U.S. Department of State’s Under Secretary for Management, the senior official overseeing the department’s administrative, budgetary, and logistical functions.
  • 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_69c688143bfc81908d4176617735e601 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ea368fb88190bd9e991e8b94dac6 completed March 27, 2026, 8:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7d38efa4c8190abd6434188d8c58f completed March 28, 2026, 1:11 p.m.
NEDg Description generation batch_69c7d476df7081909d6e26015ac9135f completed March 28, 2026, 1:15 p.m.
NED2 Entity disambiguation (via description) batch_69c7d551870c8190be0b37702d683fbd completed March 28, 2026, 1:19 p.m.
Created at: March 27, 2026, 2:55 p.m.