Triple

T3265318
Position Surface form Disambiguated ID Type / Status
Subject Lev Kerbel E68511 entity
Predicate familyName P18 FINISHED
Object Kerbel
Kerbel is a surname most notably associated with Lev Kerbel, a prominent Soviet sculptor known for his large-scale public monuments.
 E341749 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: Kerbel | Statement: [Lev Kerbel, familyName, Kerbel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kerbel
Context triple: [Lev Kerbel, familyName, Kerbel]
  • A. Starhopper
    Starhopper is SpaceX’s early prototype test vehicle used to validate key technologies for the Starship launch system, particularly its Raptor engines and vertical takeoff and landing capabilities.
  • B. Koios
    Koios is a Titan from Greek mythology associated with intelligence and the axis of heaven, often identified as the father of Leto and Asteria.
  • C. Sandage
    Sandage is a surname most notably associated with Allan R. Sandage, a prominent American astronomer known for his work on the expansion rate and age of the universe.
  • D. Antares
    Antares was the Lunar Module used in NASA’s Apollo 14 mission to land astronauts on the Moon in 1971.
  • E. Sagan
    Sagan is a town in present-day Żagań, Poland, historically known as a center where the astronomer Johannes Kepler conducted part of his scientific work.
  • 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: Kerbel
Triple: [Lev Kerbel, familyName, Kerbel]
Generated description
Kerbel is a surname most notably associated with Lev Kerbel, a prominent Soviet sculptor known for his large-scale public monuments.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kerbel
Target entity description: Kerbel is a surname most notably associated with Lev Kerbel, a prominent Soviet sculptor known for his large-scale public monuments.
  • A. Starhopper
    Starhopper is SpaceX’s early prototype test vehicle used to validate key technologies for the Starship launch system, particularly its Raptor engines and vertical takeoff and landing capabilities.
  • B. Koios
    Koios is a Titan from Greek mythology associated with intelligence and the axis of heaven, often identified as the father of Leto and Asteria.
  • C. Sandage
    Sandage is a surname most notably associated with Allan R. Sandage, a prominent American astronomer known for his work on the expansion rate and age of the universe.
  • D. Antares
    Antares was the Lunar Module used in NASA’s Apollo 14 mission to land astronauts on the Moon in 1971.
  • E. Sagan
    Sagan is a town in present-day Żagań, Poland, historically known as a center where the astronomer Johannes Kepler conducted part of his scientific work.
  • 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_69ad8590444081909e8107a8aeef3a23 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adafcc99908190897230b4b71e2ea8 completed March 8, 2026, 5:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28eed68c08190994376bfbfeae949 completed March 12, 2026, 10:01 a.m.
NEDg Description generation batch_69b2900805d08190afbda5ee5e984b71 completed March 12, 2026, 10:06 a.m.
NED2 Entity disambiguation (via description) batch_69b2ac4c52d48190a87b1e535c2e8a37 completed March 12, 2026, 12:06 p.m.
Created at: March 8, 2026, 3:09 p.m.