Triple

T16435149
Position Surface form Disambiguated ID Type / Status
Subject George Kennedy E399162 entity
Predicate spouse P13 FINISHED
Object Joan McCarthy
Joan McCarthy is best known as the wife of Academy Award–winning American actor George Kennedy.
E1306870 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: Joan McCarthy | Statement: [George Kennedy, spouse, Joan McCarthy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joan McCarthy
Context triple: [George Kennedy, spouse, Joan McCarthy]
  • A. Joan McGee
    Joan McGee is an actress known for appearing in the 1990s British television series "Career Girls."
  • B. Joan Hackett
    Joan Hackett was an American actress known for her acclaimed work in film, television, and theater during the 1960s and 1970s, often portraying complex, intelligent female characters.
  • C. Joan Towne
    Joan Towne was a 17th-century New England woman known primarily as the mother of Sarah Towne Cloyce, one of the women accused during the Salem witch trials.
  • D. Joan Hotchkis
    Joan Hotchkis was an American actress and writer known for her work in film, television, and theater during the mid-20th century.
  • E. Joan Foster
    Joan Foster is the complex, identity-shifting protagonist of Margaret Atwood’s novel "Lady Oracle," known for her secret life as a gothic romance writer and her struggle to escape her past.
  • 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: Joan McCarthy
Triple: [George Kennedy, spouse, Joan McCarthy]
Generated description
Joan McCarthy is best known as the wife of Academy Award–winning American actor George Kennedy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Joan McCarthy
Target entity description: Joan McCarthy is best known as the wife of Academy Award–winning American actor George Kennedy.
  • A. Joan McGee
    Joan McGee is an actress known for appearing in the 1990s British television series "Career Girls."
  • B. Joan Hackett
    Joan Hackett was an American actress known for her acclaimed work in film, television, and theater during the 1960s and 1970s, often portraying complex, intelligent female characters.
  • C. Joan Towne
    Joan Towne was a 17th-century New England woman known primarily as the mother of Sarah Towne Cloyce, one of the women accused during the Salem witch trials.
  • D. Joan Hotchkis
    Joan Hotchkis was an American actress and writer known for her work in film, television, and theater during the mid-20th century.
  • E. Joan Foster
    Joan Foster is the complex, identity-shifting protagonist of Margaret Atwood’s novel "Lady Oracle," known for her secret life as a gothic romance writer and her struggle to escape her past.
  • 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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32ba1023481909588aa6a3c677886 completed April 18, 2026, 6:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a037c1f2ac48190be5990748207819a completed May 12, 2026, 7:14 p.m.
NEDg Description generation batch_6a037e34ca8c81909bdaa64d3777ffb7 completed May 12, 2026, 7:23 p.m.
NED2 Entity disambiguation (via description) batch_6a037ea9aa208190b82e32b47d04a417 completed May 12, 2026, 7:25 p.m.
Created at: April 10, 2026, 5:10 a.m.