Triple

T16452634
Position Surface form Disambiguated ID Type / Status
Subject Fedor Tokarev E399590 entity
Predicate workLocation P7 FINISHED
Object Tula
Tula is a historic Russian city known as a major center of arms manufacturing and metalworking, as well as for its traditional samovars and gingerbread.
 E111344 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: Tula | Statement: [Fedor Tokarev, workLocation, Tula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tula
Context triple: [Fedor Tokarev, workLocation, Tula]
  • A. Tula
    Tula is the birth name of American actress and dancer Cyd Charisse, famed for her roles in classic Hollywood musicals.
  • B. Tula
    Tula is a small coastal village in the Eastern District of American Samoa known for its traditional Samoan culture and scenic Pacific island setting.
  • C. Tula
    Tula is a town in the Logudoro region of northern Sardinia, Italy, known for its rural landscape and traditional Sardinian culture.
  • D. Tula
    Tula is the given name of British singer, songwriter, and television personality Tulisa Contostavlos, known for her work with N-Dubz and as a judge on The X Factor UK.
  • E. Tula
    Tula is an important ancient Mesoamerican city, once a major Toltec capital known for its monumental architecture and iconic stone warrior statues.
  • 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: Tula
Triple: [Fedor Tokarev, workLocation, Tula]
Generated description
Tula is a historic Russian city known as a major center of arms manufacturing and metalworking, as well as for its traditional samovars and gingerbread.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tula
Target entity description: Tula is a historic Russian city known as a major center of arms manufacturing and metalworking, as well as for its traditional samovars and gingerbread.
  • A. Tula chosen
    Tula is a historic Russian city south of Moscow, known for its metalworking, samovar production, and as a cultural center near Leo Tolstoy’s estate at Yasnaya Polyana.
  • B. Tula
    Tula is an important ancient Mesoamerican city, once a major Toltec capital known for its monumental architecture and iconic stone warrior statues.
  • C. Tula
    Tula is a town in the Logudoro region of northern Sardinia, Italy, known for its rural landscape and traditional Sardinian culture.
  • D. Tula
    Tula is a small coastal village in the Eastern District of American Samoa known for its traditional Samoan culture and scenic Pacific island setting.
  • E. Tula
    Tula is the given name of British singer, songwriter, and television personality Tulisa Contostavlos, known for her work with N-Dubz and as a judge on The X Factor UK.
  • F. None of above.

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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32ce19344819083d323077b742bc3 completed April 18, 2026, 7:04 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004598ec088190be80ad70e3f1357e completed May 10, 2026, 8:45 a.m.
NEDg Description generation batch_6a00461390608190848c3b896042f1fd completed May 10, 2026, 8:47 a.m.
NED2 Entity disambiguation (via description) batch_6a0046a88e048190baa78506808171b8 completed May 10, 2026, 8:49 a.m.
Created at: April 10, 2026, 5:10 a.m.