Triple

T20900337
Position Surface form Disambiguated ID Type / Status
Subject Penny Fitzgerald E514651 entity
Predicate classmateOf P49703 FINISHED
Object Teri
Teri is a shy, paper-like character from the animated series "The Amazing World of Gumball," known for her anxious personality and tendency to worry about her health.
E1456588 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: Teri | Statement: [Penny Fitzgerald, classmateOf, Teri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Teri
Context triple: [Penny Fitzgerald, classmateOf, Teri]
  • A. Teri
    Teri is a central character in the film and television series "Soul Food," known as the ambitious, high-powered attorney whose strained relationships with her family drive much of the story’s drama.
  • B. Terêna
    Terêna is an Arawakan language spoken by the Terena Indigenous people of Brazil, primarily in the state of Mato Grosso do Sul.
  • C. Teressa
    Teressa is a Nicobarese language variety spoken by the indigenous community on Teressa Island in India’s Nicobar archipelago.
  • D. Terina
    Terina was an ancient Greek-founded city in southern Italy’s Bruttium region, known as a significant coastal and commercial center in Magna Graecia.
  • E. Sheilia
    Sheilia is a feminine given name, typically considered an alternative spelling of the name Sheila.
  • 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: Teri
Triple: [Penny Fitzgerald, classmateOf, Teri]
Generated description
Teri is a shy, paper-like character from the animated series "The Amazing World of Gumball," known for her anxious personality and tendency to worry about her health.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Teri
Target entity description: Teri is a shy, paper-like character from the animated series "The Amazing World of Gumball," known for her anxious personality and tendency to worry about her health.
  • A. Teri
    Teri is a central character in the film and television series "Soul Food," known as the ambitious, high-powered attorney whose strained relationships with her family drive much of the story’s drama.
  • B. Terêna
    Terêna is an Arawakan language spoken by the Terena Indigenous people of Brazil, primarily in the state of Mato Grosso do Sul.
  • C. Teressa
    Teressa is a Nicobarese language variety spoken by the indigenous community on Teressa Island in India’s Nicobar archipelago.
  • D. Terina
    Terina was an ancient Greek-founded city in southern Italy’s Bruttium region, known as a significant coastal and commercial center in Magna Graecia.
  • E. Sheilia
    Sheilia is a feminine given name, typically considered an alternative spelling of the name Sheila.
  • 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_69e0b4f8a1108190bce3d31331290ced completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8fa5228819084341dbc813cc1e3 completed April 21, 2026, 3:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0918d2b7708190acbcd7cdbb33dd23 completed May 17, 2026, 1:24 a.m.
NEDg Description generation batch_6a0919ffc9c081908adb502908bfcc84 completed May 17, 2026, 1:29 a.m.
NED2 Entity disambiguation (via description) batch_6a091a6dc2c8819090618097438a2c00 completed May 17, 2026, 1:31 a.m.
Created at: April 16, 2026, 12:47 p.m.