Triple

T9958330
Position Surface form Disambiguated ID Type / Status
Subject Russian State Historical Archive E195498 entity
Predicate shortName P43 FINISHED
Object RGIA
RGIA is the abbreviated name for the Russian State Historical Archive, one of Russia’s largest repositories of documents on the country’s political, social, and cultural history.
E831754 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: RGIA | Statement: [Russian State Historical Archive, shortName, RGIA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RGIA
Context triple: [Russian State Historical Archive, shortName, RGIA]
  • A. GIA
    GIA is the three-letter ICAO airline designator assigned to Garuda Indonesia, the national flag carrier of Indonesia.
  • B. RG
    RG is the former IATA airline designator for Varig, the now-defunct Brazilian flag carrier that was once the country’s largest airline.
  • C. RG
    RG is a postcode area in southern England covering Reading and surrounding towns in Berkshire and parts of neighbouring counties.
  • D. GRA
    GRA is the ring-shaped orbital motorway encircling Rome, Italy, serving as a major traffic artery for the metropolitan area.
  • E. CRGA
    CRGA is the acronym for the Committee of Representatives of Governments and Administrations, a body that brings together governmental and administrative representatives for coordination and decision-making.
  • 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: RGIA
Triple: [Russian State Historical Archive, shortName, RGIA]
Generated description
RGIA is the abbreviated name for the Russian State Historical Archive, one of Russia’s largest repositories of documents on the country’s political, social, and cultural history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: RGIA
Target entity description: RGIA is the abbreviated name for the Russian State Historical Archive, one of Russia’s largest repositories of documents on the country’s political, social, and cultural history.
  • A. GIA
    GIA is the three-letter ICAO airline designator assigned to Garuda Indonesia, the national flag carrier of Indonesia.
  • B. RG
    RG is a postcode area in southern England covering Reading and surrounding towns in Berkshire and parts of neighbouring counties.
  • C. RG
    RG is the former IATA airline designator for Varig, the now-defunct Brazilian flag carrier that was once the country’s largest airline.
  • D. GRA
    GRA is the ring-shaped orbital motorway encircling Rome, Italy, serving as a major traffic artery for the metropolitan area.
  • E. CRGA
    CRGA is the acronym for the Committee of Representatives of Governments and Administrations, a body that brings together governmental and administrative representatives for coordination and decision-making.
  • 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_69ca82eaaa008190a54fa1a9f954b9ad completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb6cec7dc8190bb7e43c82a317707 completed April 2, 2026, 12:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23d7988948190bae81c1020f2b605 completed April 5, 2026, 10:46 a.m.
NEDg Description generation batch_69d23e6ee6d48190ae724d0ee96b64bf completed April 5, 2026, 10:50 a.m.
NED2 Entity disambiguation (via description) batch_69d23fd274dc8190b7af27cf503d7dc6 completed April 5, 2026, 10:56 a.m.
Created at: March 30, 2026, 8:46 p.m.