Triple

T9547311
Position Surface form Disambiguated ID Type / Status
Subject Paul Devorski E230325 entity
Predicate familyName P18 FINISHED
Object Devorski
Devorski is a surname most notably associated with Paul Devorski, a former National Hockey League referee.
E805452 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: Devorski | Statement: [Paul Devorski, familyName, Devorski]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Devorski
Context triple: [Paul Devorski, familyName, Devorski]
  • A. Donoven
    Donoven is an alternative spelling of the given name Donovan, which is of Irish origin and used as a masculine first name and surname.
  • B. Shriever
    Shriever is a surname, a variant spelling of "Shriver," borne by various individuals of English-speaking origin.
  • C. Kaven
    Kaven is one of the islands that make up Maloelap Atoll in the Marshall Islands, a Pacific island nation.
  • D. Ryen
    Ryen is a residential neighborhood in Oslo, Norway, known for its apartment blocks, local amenities, and good public transport connections.
  • E. Devine
    Devine is a surname of Irish origin borne by various notable individuals across fields such as sports, politics, and the arts.
  • 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: Devorski
Triple: [Paul Devorski, familyName, Devorski]
Generated description
Devorski is a surname most notably associated with Paul Devorski, a former National Hockey League referee.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Devorski
Target entity description: Devorski is a surname most notably associated with Paul Devorski, a former National Hockey League referee.
  • A. Donoven
    Donoven is an alternative spelling of the given name Donovan, which is of Irish origin and used as a masculine first name and surname.
  • B. Shriever
    Shriever is a surname, a variant spelling of "Shriver," borne by various individuals of English-speaking origin.
  • C. Kaven
    Kaven is one of the islands that make up Maloelap Atoll in the Marshall Islands, a Pacific island nation.
  • D. Ryen
    Ryen is a residential neighborhood in Oslo, Norway, known for its apartment blocks, local amenities, and good public transport connections.
  • E. Devine
    Devine is a surname of Irish origin borne by various notable individuals across fields such as sports, politics, and the arts.
  • 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_69ca847c70b8819088a0a0bad64a50d6 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9904732c8190ab60ecc47c995cbe completed April 1, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69d14c7be5008190a16036525fd9059e completed April 4, 2026, 5:38 p.m.
NEDg Description generation batch_69d14d4576488190a000f733ece39620 completed April 4, 2026, 5:41 p.m.
NED2 Entity disambiguation (via description) batch_69d14dda805c81908093eb146915fdda completed April 4, 2026, 5:43 p.m.
Created at: March 30, 2026, 8:02 p.m.