Triple

T1882165
Position Surface form Disambiguated ID Type / Status
Subject Marinus Willett E39876 entity
Predicate familyName P18 FINISHED
Object Willett
Willett is a surname of English origin borne by various notable individuals, including American Revolutionary War officer and politician Marinus Willett.
E209828 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: Willett | Statement: [Marinus Willett, familyName, Willett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Willett
Context triple: [Marinus Willett, familyName, Willett]
  • A. Montgomerie
    Montgomerie is a variant spelling of the surname Montgomery, historically associated with Scottish nobility and clans.
  • B. Irving Green
    Irving Green was an American music executive best known as a co-founder and influential leader of Mercury Records, where he helped shape mid-20th-century popular music.
  • C. Ewart
    Ewart is a given name notably borne by the 19th-century British statesman William Ewart Gladstone.
  • D. Retief
    Retief is an Afrikaans surname of French Huguenot origin, notably borne by South African historical figures and athletes.
  • E. Barnett
    Barnett is a masculine given name most notably associated with the influential American abstract expressionist painter Barnett Newman.
  • 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: Willett
Triple: [Marinus Willett, familyName, Willett]
Generated description
Willett is a surname of English origin borne by various notable individuals, including American Revolutionary War officer and politician Marinus Willett.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Willett
Target entity description: Willett is a surname of English origin borne by various notable individuals, including American Revolutionary War officer and politician Marinus Willett.
  • A. Montgomerie
    Montgomerie is a variant spelling of the surname Montgomery, historically associated with Scottish nobility and clans.
  • B. Irving Green
    Irving Green was an American music executive best known as a co-founder and influential leader of Mercury Records, where he helped shape mid-20th-century popular music.
  • C. Ewart
    Ewart is a given name notably borne by the 19th-century British statesman William Ewart Gladstone.
  • D. Retief
    Retief is an Afrikaans surname of French Huguenot origin, notably borne by South African historical figures and athletes.
  • E. Barnett
    Barnett is a masculine given name most notably associated with the influential American abstract expressionist painter Barnett Newman.
  • 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_69a88633e4fc8190b7eb40463e048ec5 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb0fd4d6881908b8266bdae1517ce completed March 7, 2026, 5 a.m.
NED1 Entity disambiguation (via context triple) batch_69addf5eabd8819089f267db92993033 completed March 8, 2026, 8:43 p.m.
NEDg Description generation batch_69addfe604708190b85d6f7261197537 completed March 8, 2026, 8:45 p.m.
NED2 Entity disambiguation (via description) batch_69ade0919d748190a4326d4abca2c9eb completed March 8, 2026, 8:48 p.m.
Created at: March 4, 2026, 7:34 p.m.