Triple

T4333404
Position Surface form Disambiguated ID Type / Status
Subject Vardar Offensive E97405 entity
Predicate opposingCommander P1698 FINISHED
Object Georgi Todorov
Georgi Todorov was a Bulgarian general who played a prominent command role in the Balkan Wars and World War I.
E431976 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: Georgi Todorov | Statement: [Vardar Offensive, opposingCommander, Georgi Todorov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Georgi Todorov
Context triple: [Vardar Offensive, opposingCommander, Georgi Todorov]
  • A. Dimitar Blagoev
    Dimitar Blagoev was a Bulgarian political leader and theorist, known as the founder of the Bulgarian socialist movement and the Bulgarian Social Democratic Party.
  • B. Vladimir Tenev
    Vladimir Tenev is a Bulgarian-American entrepreneur best known as the co-founder and CEO of the commission-free trading platform Robinhood Markets.
  • C. Vulko Chervenkov
    Vulko Chervenkov was a Bulgarian communist politician who served as the country’s de facto leader in the early 1950s, overseeing a period of strict Stalinist rule and rapid industrialization.
  • D. Alexander Toshev
    Alexander Toshev is a computer scientist known for his contributions to computer vision and deep learning, including influential work on object detection.
  • E. Dragomir Anguelov
    Dragomir Anguelov is a computer scientist known for his work in machine learning and computer vision, particularly in 3D perception and autonomous driving.
  • 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: Georgi Todorov
Triple: [Vardar Offensive, opposingCommander, Georgi Todorov]
Generated description
Georgi Todorov was a Bulgarian general who played a prominent command role in the Balkan Wars and World War I.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Georgi Todorov
Target entity description: Georgi Todorov was a Bulgarian general who played a prominent command role in the Balkan Wars and World War I.
  • A. Dimitar Blagoev
    Dimitar Blagoev was a Bulgarian political leader and theorist, known as the founder of the Bulgarian socialist movement and the Bulgarian Social Democratic Party.
  • B. Vladimir Tenev
    Vladimir Tenev is a Bulgarian-American entrepreneur best known as the co-founder and CEO of the commission-free trading platform Robinhood Markets.
  • C. Vulko Chervenkov
    Vulko Chervenkov was a Bulgarian communist politician who served as the country’s de facto leader in the early 1950s, overseeing a period of strict Stalinist rule and rapid industrialization.
  • D. Alexander Toshev
    Alexander Toshev is a computer scientist known for his contributions to computer vision and deep learning, including influential work on object detection.
  • E. Dragomir Anguelov
    Dragomir Anguelov is a computer scientist known for his work in machine learning and computer vision, particularly in 3D perception and autonomous driving.
  • 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_69b3454662a481908fbcd0bbfaa3a0a4 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3514faaac819081475681fd10da24 completed March 12, 2026, 11:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5d0a634308190ba4d8c8dc07814ae completed March 14, 2026, 9:18 p.m.
NEDg Description generation batch_69b5d47416fc8190b8a177cbdcc23399 completed March 14, 2026, 9:34 p.m.
NED2 Entity disambiguation (via description) batch_69b5d4e5e24c8190980bc545ca0d339d completed March 14, 2026, 9:36 p.m.
Created at: March 12, 2026, 11:13 p.m.