Triple

T13865753
Position Surface form Disambiguated ID Type / Status
Subject Teddy Pendergrass E333319 entity
Predicate spouse P13 FINISHED
Object Karen Still
Karen Still is best known as the wife of legendary American R&B singer Teddy Pendergrass.
E1114737 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: Karen Still | Statement: [Teddy Pendergrass, spouse, Karen Still]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karen Still
Context triple: [Teddy Pendergrass, spouse, Karen Still]
  • A. Karen Dotrice
    Karen Dotrice is a British former child actress best known for playing Jane Banks in Disney’s classic film "Mary Poppins."
  • B. Karen Moss
    Karen Moss is the biological mother of television personality and fashion designer Nicole Richie.
  • C. Carol Stevens
    Carol Stevens is best known as one of the former wives of American novelist and journalist Norman Mailer.
  • D. Karen Roe
    Karen Roe is a central character on the television series "One Tree Hill," known as Lucas Scott’s caring and resilient single mother and a key figure in the show's community.
  • E. Karen Vick
    Karen Vick is a fictional police chief on the TV series "Psych," known for overseeing the Santa Barbara Police Department and managing the antics of Shawn Spencer and Burton Guster.
  • 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: Karen Still
Triple: [Teddy Pendergrass, spouse, Karen Still]
Generated description
Karen Still is best known as the wife of legendary American R&B singer Teddy Pendergrass.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Karen Still
Target entity description: Karen Still is best known as the wife of legendary American R&B singer Teddy Pendergrass.
  • A. Karen Dotrice
    Karen Dotrice is a British former child actress best known for playing Jane Banks in Disney’s classic film "Mary Poppins."
  • B. Karen Moss
    Karen Moss is the biological mother of television personality and fashion designer Nicole Richie.
  • C. Carol Stevens
    Carol Stevens is best known as one of the former wives of American novelist and journalist Norman Mailer.
  • D. Karen Roe
    Karen Roe is a central character on the television series "One Tree Hill," known as Lucas Scott’s caring and resilient single mother and a key figure in the show's community.
  • E. Karen Vick
    Karen Vick is a fictional police chief on the TV series "Psych," known for overseeing the Santa Barbara Police Department and managing the antics of Shawn Spencer and Burton Guster.
  • 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_69d81c5ced9c8190b0e9bcc6effe5959 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de05c419d481909230e8879b6dab5c completed April 14, 2026, 9:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69fdf06a3e208190a24e6cd9cb97e99c completed May 8, 2026, 2:17 p.m.
NEDg Description generation batch_69fdf15993e88190af2915db1584dfa1 completed May 8, 2026, 2:21 p.m.
NED2 Entity disambiguation (via description) batch_69fdf1c407208190a0b544d98551319f completed May 8, 2026, 2:23 p.m.
Created at: April 9, 2026, 10:14 p.m.