Triple

T17050408
Position Surface form Disambiguated ID Type / Status
Subject William Peters Hepburn E413678 entity
Predicate middleName P143 FINISHED
Object Peters
Peters is the middle name of American politician William Peters Hepburn, after whom he is commonly identified.
 E1248443 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: Peters | Statement: [William Peters Hepburn, middleName, Peters]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Peters
Context triple: [William Peters Hepburn, middleName, Peters]
  • A. Peters
    Peters is a set of early United States Supreme Court case reports compiled by Richard Peters, later incorporated into the official United States Reports.
  • B. Peters
    Peters is the family name of classic Hollywood film star Carole Lombard, known for her acclaimed roles in 1930s screwball comedies.
  • C. Peters
    Peters is a central crew member and medical technician aboard the rescue vessel Lewis and Clark in the 1997 science fiction horror film "Event Horizon."
  • D. Peters
    Peters is the married surname of Svetlana Iosifovna Stalina, the daughter of Soviet leader Joseph Stalin.
  • E. Peters
    Peters is the surname of the 19th-century zoologist Wilhelm Peters, a German naturalist known for describing numerous animal species.
  • 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: Peters
Triple: [William Peters Hepburn, middleName, Peters]
Generated description
Peters is the middle name of American politician William Peters Hepburn, after whom he is commonly identified.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Peters
Target entity description: Peters is the middle name of American politician William Peters Hepburn, after whom he is commonly identified.
  • A. Peters
    Peters is a surname of English and German origin borne by numerous notable individuals across various fields.
  • B. Peters
    Peters is the surname of the 19th-century zoologist Wilhelm Peters, a German naturalist known for describing numerous animal species.
  • C. Peters
    Peters is the family name of classic Hollywood film star Carole Lombard, known for her acclaimed roles in 1930s screwball comedies.
  • D. Peters
    Peters is the married surname of Svetlana Iosifovna Stalina, the daughter of Soviet leader Joseph Stalin.
  • E. Peters
    Peters is a set of early United States Supreme Court case reports compiled by Richard Peters, later incorporated into the official United States Reports.
  • 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_69d886cde3d481908d4d01ba88ba7eb7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3daa1aeac81909e8d97bd708c6b71 completed April 18, 2026, 7:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012341b8e88190a2bee865be5ca1c1 completed May 11, 2026, 12:30 a.m.
NEDg Description generation batch_6a012585a1548190a112f55e2d84ccac completed May 11, 2026, 12:40 a.m.
NED2 Entity disambiguation (via description) batch_6a0126536c348190b9b2eadb4969f8c2 completed May 11, 2026, 12:44 a.m.
Created at: April 10, 2026, 5:34 a.m.