Triple

T1749519
Position Surface form Disambiguated ID Type / Status
Subject Lie to Me E38406 entity
Predicate starring P1507 FINISHED
Object Kelli Williams
Kelli Williams is an American actress best known for her television roles in series such as "The Practice" and "Lie to Me."
 E302397 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: Kelli Williams | Statement: [Lie to Me, starring, Kelli Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kelli Williams
Context triple: [Lie to Me, starring, Kelli Williams]
  • A. Kellie Miller
    Kellie Miller is one of the plaintiffs who challenged Tennessee’s ban on recognizing same-sex marriages in the federal court case Tanco v. Haslam.
  • B. Jennifer Williams
    Jennifer Williams is known as the daughter of acclaimed American composer and conductor John Williams.
  • C. Kimberlee Acquaro
    Kimberlee Acquaro is an American filmmaker, journalist, and activist known for her documentaries and writing on social justice, gender, and human rights issues.
  • D. Kay Williams
    Kay Williams was an American actress and the fifth and final wife of Hollywood star Clark Gable.
  • E. Amanda Clayton
    Amanda Clayton is an American actress best known for her role in the crime drama television series "City on a Hill."
  • 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: Kelli Williams
Triple: [Lie to Me, starring, Kelli Williams]
Generated description
Kelli Williams is an American actress best known for her television roles in series such as "The Practice" and "Lie to Me."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kelli Williams
Target entity description: Kelli Williams is an American actress best known for her television roles in series such as "The Practice" and "Lie to Me."
  • A. Kellie Miller
    Kellie Miller is one of the plaintiffs who challenged Tennessee’s ban on recognizing same-sex marriages in the federal court case Tanco v. Haslam.
  • B. Jennifer Williams
    Jennifer Williams is known as the daughter of acclaimed American composer and conductor John Williams.
  • C. Kimberlee Acquaro
    Kimberlee Acquaro is an American filmmaker, journalist, and activist known for her documentaries and writing on social justice, gender, and human rights issues.
  • D. Kay Williams
    Kay Williams was an American actress and the fifth and final wife of Hollywood star Clark Gable.
  • E. Amanda Clayton
    Amanda Clayton is an American actress best known for her role in the crime drama television series "City on a Hill."
  • 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_69a8862bdb2081908aefe831c8aa8017 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa63ee4d2081909dfd6d3244228c56 completed March 6, 2026, 5:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69afce7154648190aa55d54ca5e50559 completed March 10, 2026, 7:55 a.m.
NEDg Description generation batch_69afd22a81dc8190809f94f8e49ddad8 completed March 10, 2026, 8:11 a.m.
NED2 Entity disambiguation (via description) batch_69afd3b8daec81908c5d507e35ba997e completed March 10, 2026, 8:18 a.m.
Created at: March 4, 2026, 7:31 p.m.