Triple

T10584957
Position Surface form Disambiguated ID Type / Status
Subject G. Mennen Williams E249831 entity
Predicate nickname P55 FINISHED
Object Soapy
Soapy was the nickname of G. Mennen Williams, a prominent mid-20th-century American politician who served as governor of Michigan and later as a U.S. diplomat.
E873187 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: Soapy | Statement: [G. Mennen Williams, nickname, Soapy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soapy
Context triple: [G. Mennen Williams, nickname, Soapy]
  • A. Sandy-boy
    Sandy-boy is a diminutive or affectionate nickname derived from the given name Sandy.
  • B. Maripipi
    Maripipi is a small island municipality in the province of Biliran in the Eastern Visayas region of the Philippines, known for its coastal communities and scenic marine environment.
  • C. Wide Boy
    "Wide Boy" is a song by the English art pop duo Godley & Creme, known for their inventive music and pioneering music videos.
  • D. The Eddy
    The Eddy is a musical drama miniseries set in a Paris jazz club, created by Damien Chazelle and known for its immersive live music performances and gritty, character-driven storytelling.
  • E. The Soup
    The Soup was a satirical television series on E! that humorously recapped and mocked clips from various reality shows, talk shows, and other pop culture programming.
  • 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: Soapy
Triple: [G. Mennen Williams, nickname, Soapy]
Generated description
Soapy was the nickname of G. Mennen Williams, a prominent mid-20th-century American politician who served as governor of Michigan and later as a U.S. diplomat.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Soapy
Target entity description: Soapy was the nickname of G. Mennen Williams, a prominent mid-20th-century American politician who served as governor of Michigan and later as a U.S. diplomat.
  • A. Sandy-boy
    Sandy-boy is a diminutive or affectionate nickname derived from the given name Sandy.
  • B. Maripipi
    Maripipi is a small island municipality in the province of Biliran in the Eastern Visayas region of the Philippines, known for its coastal communities and scenic marine environment.
  • C. Wide Boy
    "Wide Boy" is a song by the English art pop duo Godley & Creme, known for their inventive music and pioneering music videos.
  • D. The Eddy
    The Eddy is a musical drama miniseries set in a Paris jazz club, created by Damien Chazelle and known for its immersive live music performances and gritty, character-driven storytelling.
  • E. The Soup
    The Soup was a satirical television series on E! that humorously recapped and mocked clips from various reality shows, talk shows, and other pop culture programming.
  • 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_69d381c9d3d48190a29ee491e1696a0e completed April 6, 2026, 9:50 a.m.
NER Named-entity recognition batch_69d52768da9c8190add1db88bf2e16ea completed April 7, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69d94b820330819090ed70c6ba29b5c2 completed April 10, 2026, 7:12 p.m.
NEDg Description generation batch_69d94d67e16481908efb939a3e65004c completed April 10, 2026, 7:20 p.m.
NED2 Entity disambiguation (via description) batch_69d95227a1f48190ab847606a9ae0500 completed April 10, 2026, 7:40 p.m.
Created at: April 6, 2026, 12:39 p.m.