Triple

T6555705
Position Surface form Disambiguated ID Type / Status
Subject Tom Berenger E152440 entity
Predicate spouse P13 FINISHED
Object Lisa Williams
Lisa Williams is known as the former wife of American actor Tom Berenger.
E604762 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: Lisa Williams | Statement: [Tom Berenger, spouse, Lisa Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisa Williams
Context triple: [Tom Berenger, spouse, Lisa Williams]
  • A. Kay Williams
    Kay Williams was an American actress and the fifth and final wife of Hollywood star Clark Gable.
  • B. Courtney Hodges
    Courtney Hodges was a senior U.S. Army general in World War II who led First Army in Western Europe, playing a key role in the Allied advance from Normandy into Germany.
  • C. Jennifer Williams
    Jennifer Williams is known as the daughter of acclaimed American composer and conductor John Williams.
  • D. Saffron Aldridge
    Saffron Aldridge is a British fashion model known for her work in the 1990s, including campaigns for brands like Ralph Lauren and Calvin Klein.
  • E. Mechelle Vinson
    Mechelle Vinson is the woman whose sexual harassment lawsuit led to the landmark U.S. Supreme Court case Meritor Savings Bank v. Vinson, which established that a hostile work environment can violate Title VII of the Civil Rights Act.
  • 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: Lisa Williams
Triple: [Tom Berenger, spouse, Lisa Williams]
Generated description
Lisa Williams is known as the former wife of American actor Tom Berenger.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lisa Williams
Target entity description: Lisa Williams is known as the former wife of American actor Tom Berenger.
  • A. Kay Williams
    Kay Williams was an American actress and the fifth and final wife of Hollywood star Clark Gable.
  • B. Courtney Hodges
    Courtney Hodges was a senior U.S. Army general in World War II who led First Army in Western Europe, playing a key role in the Allied advance from Normandy into Germany.
  • C. Jennifer Williams
    Jennifer Williams is known as the daughter of acclaimed American composer and conductor John Williams.
  • D. Saffron Aldridge
    Saffron Aldridge is a British fashion model known for her work in the 1990s, including campaigns for brands like Ralph Lauren and Calvin Klein.
  • E. Mechelle Vinson
    Mechelle Vinson is the woman whose sexual harassment lawsuit led to the landmark U.S. Supreme Court case Meritor Savings Bank v. Vinson, which established that a hostile work environment can violate Title VII of the Civil Rights Act.
  • 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_69c688058d6881908c19b309cc55dbfa completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ae1d28bc8190a2fa4b3e1e39863c completed March 27, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6d559ad4881909c1e7712d84945f6 completed March 27, 2026, 7:07 p.m.
NEDg Description generation batch_69c6d676e43081909bf2a9cceff0b9b3 completed March 27, 2026, 7:11 p.m.
NED2 Entity disambiguation (via description) batch_69c6d84076d48190ada0903af49613de completed March 27, 2026, 7:19 p.m.
Created at: March 27, 2026, 1:51 p.m.