Triple

T18285151
Position Surface form Disambiguated ID Type / Status
Subject Georgi Rakovski E437962 entity
Predicate givenName P17 FINISHED
Object Georgi NE NERFINISHED

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 | Statement: [Georgi Rakovski, givenName, Georgi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Georgi
Context triple: [Georgi Rakovski, givenName, Georgi]
  • A. Georgi chosen
    Georgi is a common Bulgarian male given name, widely used across Slavic countries and derived from the Greek name Georgios.
  • B. Georgy Georgiu
    Georgy Georgiu is an actor known for his role in the Soviet adventure-comedy film "Gentlemen of Fortune."
  • C. Georgii
    Georgii is a masculine given name, commonly used in Slavic countries as a variant of George.
  • D. Lyuben
    Lyuben is a masculine given name of Slavic origin, commonly used in Bulgaria and other Slavic countries.
  • E. Kimon Georgiev
    Kimon Georgiev was a Bulgarian military officer and politician who twice served as prime minister and played a leading role in several coups that reshaped Bulgaria’s 20th-century political landscape.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e500f913d48190b41a1e37ca05e8b1 completed April 19, 2026, 4:21 p.m.
Created at: April 10, 2026, 10:35 a.m.