Triple

T10090040
Position Surface form Disambiguated ID Type / Status
Subject Elmo Williams E215318 entity
Predicate spouse P13 FINISHED
Object Lorraine Williams
Lorraine Williams is known as the wife of Academy Award–winning film editor and producer Elmo Williams.
E912221 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: Lorraine Williams | Statement: [Elmo Williams, spouse, Lorraine Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lorraine Williams
Context triple: [Elmo Williams, spouse, Lorraine Williams]
  • A. Lorraine Nicholson
    Lorraine Nicholson is an American actress and filmmaker known for roles in films like "Click" and "Soul Surfer" and for being the daughter of actor Jack Nicholson.
  • B. Lorraine Baines
    Lorraine Baines is a central character in the "Back to the Future" film series, best known as Marty McFly’s mother whose teenage life in 1955 becomes the focus of his time-traveling adventures.
  • C. Yolanda Williams
    Yolanda Williams is best known as the wife of legendary American boxer Muhammad Ali.
  • D. Lorraine Miller
    Lorraine Miller was an American actress and dancer active in Hollywood films during the 1940s and 1950s.
  • E. Sharon Williams
    Sharon Williams is known for being the first wife of acclaimed film director James Cameron.
  • 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: Lorraine Williams
Triple: [Elmo Williams, spouse, Lorraine Williams]
Generated description
Lorraine Williams is known as the wife of Academy Award–winning film editor and producer Elmo Williams.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lorraine Williams
Target entity description: Lorraine Williams is known as the wife of Academy Award–winning film editor and producer Elmo Williams.
  • A. Lorraine Nicholson
    Lorraine Nicholson is an American actress and filmmaker known for roles in films like "Click" and "Soul Surfer" and for being the daughter of actor Jack Nicholson.
  • B. Lorraine Baines
    Lorraine Baines is a central character in the "Back to the Future" film series, best known as Marty McFly’s mother whose teenage life in 1955 becomes the focus of his time-traveling adventures.
  • C. Yolanda Williams
    Yolanda Williams is best known as the wife of legendary American boxer Muhammad Ali.
  • D. Lorraine Miller
    Lorraine Miller was an American actress and dancer active in Hollywood films during the 1940s and 1950s.
  • E. Sharon Williams
    Sharon Williams is known for being the first wife of acclaimed film director James Cameron.
  • 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_69ca83a1eed081908b2e9580f2ebeea7 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd05960008190baecb8e4c9f2461f completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69e4aca16a10819097bb8655c8c1a36d completed April 19, 2026, 10:21 a.m.
NEDg Description generation batch_69e4afa531e0819097587675198bb8a1 completed April 19, 2026, 10:34 a.m.
NED2 Entity disambiguation (via description) batch_69e4b1f68c8c819096d58ac02d76ec0d completed April 19, 2026, 10:44 a.m.
Created at: March 30, 2026, 9:01 p.m.