Triple

T9640581
Position Surface form Disambiguated ID Type / Status
Subject Nadym Airport E233053 entity
Predicate hasICAOCode P419 FINISHED
Object USMM
USMM is the ICAO airport code assigned to Nadym Airport in Russia’s Yamalo-Nenets Autonomous Okrug.
 E812630 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: USMM | Statement: [Nadym Airport, hasICAOCode, USMM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: USMM
Context triple: [Nadym Airport, hasICAOCode, USMM]
  • A. USMS
    USMS is the abbreviation for the United States Maritime Service, a federal organization responsible for training and developing personnel for the U.S. merchant marine and maritime industry.
  • B. USMS
    USMS is the federal law enforcement agency responsible for protecting the federal judiciary, managing and transporting prisoners, and executing federal court orders in the United States.
  • C. USPMM
    USPMM is the port code designating the Portland International Marine Terminal in Portland, Maine, a commercial cargo and container shipping facility.
  • D. UMS
    UMS is the public university system that oversees multiple campuses and educational institutions across the state of Maine.
  • E. UMS
    UMS is a public university system in the U.S. state of Missouri that oversees multiple campuses, including the University of Missouri in Columbia.
  • 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: USMM
Triple: [Nadym Airport, hasICAOCode, USMM]
Generated description
USMM is the ICAO airport code assigned to Nadym Airport in Russia’s Yamalo-Nenets Autonomous Okrug.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: USMM
Target entity description: USMM is the ICAO airport code assigned to Nadym Airport in Russia’s Yamalo-Nenets Autonomous Okrug.
  • A. USMS
    USMS is the federal law enforcement agency responsible for protecting the federal judiciary, managing and transporting prisoners, and executing federal court orders in the United States.
  • B. USMS
    USMS is the abbreviation for the United States Maritime Service, a federal organization responsible for training and developing personnel for the U.S. merchant marine and maritime industry.
  • C. USPMM
    USPMM is the port code designating the Portland International Marine Terminal in Portland, Maine, a commercial cargo and container shipping facility.
  • D. UMS
    UMS is the public university system that oversees multiple campuses and educational institutions across the state of Maine.
  • E. UMS
    UMS is a public university system in the U.S. state of Missouri that oversees multiple campuses, including the University of Missouri in Columbia.
  • 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_69ca848a5a908190aad251f4137b0c3a completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9b552a1c81909a1fab347110eeb1 completed April 1, 2026, 10:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69d18248ffe4819095d4ea20951eca01 completed April 4, 2026, 9:27 p.m.
NEDg Description generation batch_69d1864bd0b881908806762ce9df3029 completed April 4, 2026, 9:44 p.m.
NED2 Entity disambiguation (via description) batch_69d186d03eac8190a1080d5c25f4643c completed April 4, 2026, 9:46 p.m.
Created at: March 30, 2026, 8:12 p.m.