Triple

T705472
Position Surface form Disambiguated ID Type / Status
Subject Guatemala E14088 entity
Predicate ISO3166-1Alpha3 P189 FINISHED
Object GTM
GTM is the three-letter ISO 3166-1 alpha-3 country code assigned to Guatemala.
 E84174 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: GTM | Statement: [Guatemala, ISO3166-1Alpha3, GTM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GTM
Context triple: [Guatemala, ISO3166-1Alpha3, GTM]
  • A. GTS
    GTS is an abbreviation commonly used for the Global Telecommunication System, an international network for exchanging meteorological data.
  • B. UTM
    UTM is the University of Toronto Mississauga, a suburban campus of the University of Toronto located in Mississauga, Ontario.
  • C. GPC
    GPC is the GNU Pascal Compiler, a free, open-source Pascal compiler that is part of the GNU Compiler Collection (GCC) project.
  • D. Google Analytics 4
    Google Analytics 4 is Google’s latest-generation web and app analytics platform that tracks user behavior across devices and channels to provide privacy-focused, event-based insights for marketers and businesses.
  • E. GTE
    GTE (General Telephone & Electronics Corporation) was a major U.S. telecommunications company that became one of the largest local telephone service providers before ultimately merging into Verizon.
  • 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: GTM
Triple: [Guatemala, ISO3166-1Alpha3, GTM]
Generated description
GTM is the three-letter ISO 3166-1 alpha-3 country code assigned to Guatemala.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GTM
Target entity description: GTM is the three-letter ISO 3166-1 alpha-3 country code assigned to Guatemala.
  • A. GTS
    GTS is an abbreviation commonly used for the Global Telecommunication System, an international network for exchanging meteorological data.
  • B. UTM
    UTM is the University of Toronto Mississauga, a suburban campus of the University of Toronto located in Mississauga, Ontario.
  • C. GPC
    GPC is the GNU Pascal Compiler, a free, open-source Pascal compiler that is part of the GNU Compiler Collection (GCC) project.
  • D. Google Analytics 4
    Google Analytics 4 is Google’s latest-generation web and app analytics platform that tracks user behavior across devices and channels to provide privacy-focused, event-based insights for marketers and businesses.
  • E. GTE
    GTE (General Telephone & Electronics Corporation) was a major U.S. telecommunications company that became one of the largest local telephone service providers before ultimately merging into Verizon.
  • 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_69a493494ec48190ae6751683625a9ba completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a544e3608190ac315c7aa9f88e7e completed March 1, 2026, 8:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5dcb1795c8190a178e14509b8b271 completed March 2, 2026, 6:53 p.m.
NEDg Description generation batch_69a5de4387f081909fc3f7c7db03a375 completed March 2, 2026, 7 p.m.
NED2 Entity disambiguation (via description) batch_69a5ff6bcbd8819089f7a303a6a491a8 completed March 2, 2026, 9:21 p.m.
Created at: March 1, 2026, 7:36 p.m.