Triple

T5120936
Position Surface form Disambiguated ID Type / Status
Subject Battle of Doiran E115460 entity
Predicate commanderBulgarianSide P14510 FINISHED
Object Georgi Todorov E431976 NE 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: Georgi Todorov | Statement: [Battle of Doiran, commanderBulgarianSide, Georgi Todorov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Georgi Todorov
Context triple: [Battle of Doiran, commanderBulgarianSide, Georgi Todorov]
  • A. Georgi Todorov chosen
    Georgi Todorov was a Bulgarian general who played a prominent command role in the Balkan Wars and World War I.
  • B. 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.
  • C. 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.
  • D. 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.
  • E. Alexander Toshev
    Alexander Toshev is a computer scientist known for his contributions to computer vision and deep learning, including influential work on object detection.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69bd4442ade0819087b9461f892b206b completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd846dfb908190827fbee5a5ae55e2 completed March 20, 2026, 5:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69bec4b0578c819081ad7554bafafe49 completed March 21, 2026, 4:17 p.m.
Created at: March 20, 2026, 1:42 p.m.