Triple

T2364263
Position Surface form Disambiguated ID Type / Status
Subject United States Ambassador to the Soviet Union E47344 entity
Predicate residenceFunction P31237 FINISHED
Object official residence of the U.S. ambassador in Moscow LITERAL FINISHED

How this triple was built (2 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: official residence of the U.S. ambassador in Moscow | Statement: [United States Ambassador to the Soviet Union, residenceFunction, official residence of the U.S. ambassador in Moscow]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: residenceFunction
Context triple: [United States Ambassador to the Soviet Union, residenceFunction, official residence of the U.S. ambassador in Moscow]
  • A. residence
    Indicates that one entity lives at, is based in, or habitually occupies the location represented by the other entity.
  • B. residenceType
    Indicates the kind or category of dwelling or living arrangement associated with an entity.
  • C. hasResidenceIn
    Indicates that an entity lives or maintains a primary dwelling in a specified location.
  • D. houseFunction chosen
    Indicates the functional role or primary use that a house serves (e.g., residential, commercial, mixed-use).
  • E. residencyPattern
    Indicates the typical way an entity resides or occupies a place over time, such as its usual location, duration, or frequency of stay.
  • F. None of above.

Provenance (3 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_69a88a1a4a6081908645b0f2914521ab completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abc746e7048190a09a38401b367628 completed March 7, 2026, 6:35 a.m.
PD Predicate disambiguation batch_69abc599b92c819093d9e15d4437705d completed March 7, 2026, 6:28 a.m.
Created at: March 4, 2026, 7:55 p.m.