Triple

T373668
Position Surface form Disambiguated ID Type / Status
Subject George F. Kennan E8323 entity
Predicate middleName P143 FINISHED
Object Frost
Frost is the middle name of George F. Kennan, the influential American diplomat and historian known for shaping the U.S. Cold War containment strategy.
 E47340 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: Frost | Statement: [George F. Kennan, middleName, Frost]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Frost
Context triple: [George F. Kennan, middleName, Frost]
  • A. Ice March
    The Ice March was a grueling winter retreat of White Army forces during the Russian Civil War, marked by extreme hardship and heavy losses.
  • B. Icestorm
    Icestorm is the energy-efficient, low-power CPU core microarchitecture used for the efficiency cores in Apple's M1 system-on-a-chip.
  • C. Snowflake
    Snowflake is a cloud-based data warehousing platform known for its scalable, high-performance analytics and separation of storage and compute.
  • D. Crius
    Crius is one of the twelve primordial Titans of Greek mythology, associated with the constellations and the cosmic order preceding the Olympian gods.
  • E. Fall Blau
    Fall Blau was the German Wehrmacht’s 1942 summer offensive on the Eastern Front aimed at capturing the oil fields of the Caucasus and advancing toward Stalingrad during World War II.
  • 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: Frost
Triple: [George F. Kennan, middleName, Frost]
Generated description
Frost is the middle name of George F. Kennan, the influential American diplomat and historian known for shaping the U.S. Cold War containment strategy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Frost
Target entity description: Frost is the middle name of George F. Kennan, the influential American diplomat and historian known for shaping the U.S. Cold War containment strategy.
  • A. Ice March
    The Ice March was a grueling winter retreat of White Army forces during the Russian Civil War, marked by extreme hardship and heavy losses.
  • B. Icestorm
    Icestorm is the energy-efficient, low-power CPU core microarchitecture used for the efficiency cores in Apple's M1 system-on-a-chip.
  • C. Snowflake
    Snowflake is a cloud-based data warehousing platform known for its scalable, high-performance analytics and separation of storage and compute.
  • D. Crius
    Crius is one of the twelve primordial Titans of Greek mythology, associated with the constellations and the cosmic order preceding the Olympian gods.
  • E. Fall Blau
    Fall Blau was the German Wehrmacht’s 1942 summer offensive on the Eastern Front aimed at capturing the oil fields of the Caucasus and advancing toward Stalingrad during World War II.
  • 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_69a2e7f2ec648190b42bc7db424f8109 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec13b9b48190b294d998c6720132 completed Feb. 28, 2026, 1:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3f0a9608481908bee4d83768e6497 completed March 1, 2026, 7:54 a.m.
NEDg Description generation batch_69a3f131d1f88190ac131204c5402687 completed March 1, 2026, 7:56 a.m.
NED2 Entity disambiguation (via description) batch_69a3f202f308819098affb41d502d5fb completed March 1, 2026, 8 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.