Triple

T14235141
Position Surface form Disambiguated ID Type / Status
Subject Son in Law E352857 entity
Predicate screenwriter P2831 FINISHED
Object Susan McMartin
Susan McMartin is an American television and film writer best known for her work on series such as "Mom" and "Two and a Half Men."
E1180792 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: Susan McMartin | Statement: [Son in Law, screenwriter, Susan McMartin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susan McMartin
Context triple: [Son in Law, screenwriter, Susan McMartin]
  • A. Susan Dougan
    Susan Dougan is a Vincentian public figure who serves as the Governor-General and de facto representative of the British monarch in Saint Vincent and the Grenadines.
  • B. Ann McMillan
    Ann McMillan is the daughter of American physicist and Nobel laureate Edwin McMillan.
  • C. Susan Egan
    Susan Egan is an American actress and singer best known for originating the role of Belle in Broadway’s Beauty and the Beast and voicing Megara in Disney’s animated film Hercules.
  • D. Susan Wakley
    Susan Wakley is best known as the wife of Pro Football Hall of Famer and longtime sportscaster Merlin Olsen.
  • E. Lisa McGrillis
    Lisa McGrillis is a British actress known for her work in television, film, and theatre, including roles in series like "Inspector George Gently" and "Mum."
  • 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: Susan McMartin
Triple: [Son in Law, screenwriter, Susan McMartin]
Generated description
Susan McMartin is an American television and film writer best known for her work on series such as "Mom" and "Two and a Half Men."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Susan McMartin
Target entity description: Susan McMartin is an American television and film writer best known for her work on series such as "Mom" and "Two and a Half Men."
  • A. Susan Dougan
    Susan Dougan is a Vincentian public figure who serves as the Governor-General and de facto representative of the British monarch in Saint Vincent and the Grenadines.
  • B. Ann McMillan
    Ann McMillan is the daughter of American physicist and Nobel laureate Edwin McMillan.
  • C. Susan Egan
    Susan Egan is an American actress and singer best known for originating the role of Belle in Broadway’s Beauty and the Beast and voicing Megara in Disney’s animated film Hercules.
  • D. Susan Wakley
    Susan Wakley is best known as the wife of Pro Football Hall of Famer and longtime sportscaster Merlin Olsen.
  • E. Lisa McGrillis
    Lisa McGrillis is a British actress known for her work in television, film, and theatre, including roles in series like "Inspector George Gently" and "Mum."
  • 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_69d8278adc7c8190a9218d69bce3c4e6 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de62411c888190a154acd56fe3fcaf completed April 14, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa9280ed081908030a4bbea80398c completed May 9, 2026, 9:37 p.m.
NEDg Description generation batch_69ffaa5d8860819090dc3e36a32dfb3a completed May 9, 2026, 9:42 p.m.
NED2 Entity disambiguation (via description) batch_69ffaab523dc8190bbf3cd271852493b completed May 9, 2026, 9:44 p.m.
Created at: April 10, 2026, 1:07 a.m.