Triple

T19582698
Position Surface form Disambiguated ID Type / Status
Subject Williams Timberhill Cemetery E490034 entity
Predicate hasNamePart P5298 FINISHED
Object Williams
Williams is a surname and place name commonly used in English-speaking countries for people, towns, institutions, and landmarks.
E81905 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: Williams | Statement: [Williams Timberhill Cemetery, hasNamePart, Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Williams
Context triple: [Williams Timberhill Cemetery, hasNamePart, Williams]
  • A. John
    John is the given name of John Henry Patterson, an American industrialist and founder of the National Cash Register Company.
  • B. John
    John B. Magruder was a Confederate major general during the American Civil War, known for his leadership in the Peninsula Campaign and his flamboyant personality.
  • C. John
    John is the given name of American journalist and politician John Weiss Forney, known for his influential role in 19th-century U.S. media and Democratic Party politics.
  • D. John
    John Bacon was a 19th-century American politician who served in the Wisconsin State Assembly.
  • E. John
    John is the given first name of Buck Freeman, an American professional baseball player from the late 19th and early 20th centuries.
  • 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: Williams
Triple: [Williams Timberhill Cemetery, hasNamePart, Williams]
Generated description
Williams is a surname and place name commonly used in English-speaking countries for people, towns, institutions, and landmarks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Williams
Target entity description: Williams is a surname and place name commonly used in English-speaking countries for people, towns, institutions, and landmarks.
  • A. Williams chosen
    Williams is a common English surname borne by numerous notable figures across sports, politics, arts, and entertainment.
  • B. Williams
    Williams is a small historic town in northern Arizona known as a gateway to the Grand Canyon and for its preserved Route 66 charm.
  • C. Williams
    Williams is a renowned British Formula One racing team and constructor known for its multiple World Championship titles and long-standing presence in the sport.
  • D. Williams
    Williams is a small rural town in Western Australia’s Wheatbelt region, known as a service and farming community along the Albany Highway.
  • E. Williams
    Williams is the vehicle registration code used on license plates to identify vehicles registered in Williams County, Ohio.
  • 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_69d8e8dd9374819098e36349b3211663 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6404e18f88190b7fec59499dd25e8 completed April 20, 2026, 3:03 p.m.
NED1 Entity disambiguation (via context triple) batch_6a075f0f48b88190874f8cada3ed053d completed May 15, 2026, 5:59 p.m.
NEDg Description generation batch_6a07601bb12c81909faab959182b1863 completed May 15, 2026, 6:04 p.m.
NED2 Entity disambiguation (via description) batch_6a07613541688190821fd97e069691a5 completed May 15, 2026, 6:08 p.m.
Created at: April 10, 2026, 1:42 p.m.