Triple

T11277212
Position Surface form Disambiguated ID Type / Status
Subject Ray Walston E266966 entity
Predicate givenName P17 FINISHED
Object Herman
Herman is the given first name of American actor Ray Walston, known for his roles in "My Favorite Martian" and "Fast Times at Ridgemont High."
E916389 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: Herman | Statement: [Ray Walston, givenName, Herman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Herman
Context triple: [Ray Walston, givenName, Herman]
  • A. Herman
    Herman is a surname most notably associated with Edward S. Herman, an American economist, media analyst, and critic of U.S. foreign policy.
  • B. Herman
    Herman is the given name of Belgian politician Herman De Croo, a long-serving liberal statesman and former President of the Belgian Chamber of Representatives.
  • C. Herman
    Herman is the middle name of legendary American baseball player Babe Ruth, whose full name was George Herman Ruth Jr.
  • D. Herman
    Herman is a person known by the given name Herman, associated with the role or title of Junior Cook.
  • E. Herman
    Herman is the given first name of the American blues singer and harmonica player Junior Parker.
  • 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: Herman
Triple: [Ray Walston, givenName, Herman]
Generated description
Herman is the given first name of American actor Ray Walston, known for his roles in "My Favorite Martian" and "Fast Times at Ridgemont High."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Herman
Target entity description: Herman is the given first name of American actor Ray Walston, known for his roles in "My Favorite Martian" and "Fast Times at Ridgemont High."
  • A. Herman
    Herman is a surname most notably associated with Edward S. Herman, an American economist, media analyst, and critic of U.S. foreign policy.
  • B. Herman
    Herman is the given name of Belgian politician Herman De Croo, a long-serving liberal statesman and former President of the Belgian Chamber of Representatives.
  • C. Herman
    Herman is the middle name of legendary American baseball player Babe Ruth, whose full name was George Herman Ruth Jr.
  • D. Herman
    Herman is the given first name of the American blues singer and harmonica player Junior Parker.
  • E. Herman
    Herman is a person known by the given name Herman, associated with the role or title of Junior Cook.
  • 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_69d6aac8c2f48190ad0596f1f89f0470 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e967ebb4819080b09ed3cec44e77 completed April 9, 2026, 6:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69e4f455f0bc8190994c57264f775f60 completed April 19, 2026, 3:27 p.m.
NEDg Description generation batch_69e4f95be4b08190bebb2078406cb7ba completed April 19, 2026, 3:48 p.m.
NED2 Entity disambiguation (via description) batch_69e4ff5881b8819080f9662a0c2d486d completed April 19, 2026, 4:14 p.m.
Created at: April 8, 2026, 9:31 p.m.