Triple

T4397015
Position Surface form Disambiguated ID Type / Status
Subject GUM department store E99515 entity
Predicate shortName P43 FINISHED
Object GUM
GUM is a historic and iconic department store located on Red Square in Moscow, Russia, known for its grand architecture and luxury retail offerings.
 E435979 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: GUM | Statement: [GUM department store, shortName, GUM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GUM
Context triple: [GUM department store, shortName, GUM]
  • A. GUM
    GUM is the IATA airport code for Antonio B. Won Pat International Airport, the main commercial airport serving Guam in the western Pacific.
  • B. Gumm
    Gumm is the birth surname of American actress and singer Judy Garland, originally Frances Ethel Gumm.
  • C. MUC
    MUC is the abbreviation for the Meritorious Unit Commendation, a U.S. military unit award recognizing exceptionally meritorious conduct in the performance of outstanding services.
  • D. MUC
    MUC is the IATA airport code for Munich Airport, a major international aviation hub in Germany.
  • E. GROM
    GROM is Poland’s elite special operations unit renowned for high-risk counterterrorism, hostage rescue, and unconventional warfare missions.
  • 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: GUM
Triple: [GUM department store, shortName, GUM]
Generated description
GUM is a historic and iconic department store located on Red Square in Moscow, Russia, known for its grand architecture and luxury retail offerings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GUM
Target entity description: GUM is a historic and iconic department store located on Red Square in Moscow, Russia, known for its grand architecture and luxury retail offerings.
  • A. GUM
    GUM is the IATA airport code for Antonio B. Won Pat International Airport, the main commercial airport serving Guam in the western Pacific.
  • B. Gumm
    Gumm is the birth surname of American actress and singer Judy Garland, originally Frances Ethel Gumm.
  • C. MUC
    MUC is the IATA airport code for Munich Airport, a major international aviation hub in Germany.
  • D. MUC
    MUC is the abbreviation for the Meritorious Unit Commendation, a U.S. military unit award recognizing exceptionally meritorious conduct in the performance of outstanding services.
  • E. GROM
    GROM is Poland’s elite special operations unit renowned for high-risk counterterrorism, hostage rescue, and unconventional warfare missions.
  • 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_69b345506b408190b0e3dee616738a7d completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b352aca86c8190b5af7e6600072066 completed March 12, 2026, 11:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5e53ae7bc8190b216319e522b11c6 completed March 14, 2026, 10:46 p.m.
NEDg Description generation batch_69b5e5f8b9bc8190abb35710e2ddbe5e completed March 14, 2026, 10:49 p.m.
NED2 Entity disambiguation (via description) batch_69b5e62af694819086b3eddb71f591d2 completed March 14, 2026, 10:50 p.m.
Created at: March 12, 2026, 11:20 p.m.