Triple

T6999340
Position Surface form Disambiguated ID Type / Status
Subject Rachel Maddow E162294 entity
Predicate partner P1136 FINISHED
Object Susan Mikula
Susan Mikula is an American artist and photographer known for her distinctive, often experimental photographic work and for her long-term relationship with television host Rachel Maddow.
 E639035 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 Mikula | Statement: [Rachel Maddow, partner, Susan Mikula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Susan Mikula
Context triple: [Rachel Maddow, partner, Susan Mikula]
  • A. Janine Melnitz
    Janine Melnitz is the Ghostbusters’ sharp-tongued, no-nonsense receptionist who provides comic relief and grounded support to the team.
  • B. Margo Dydek
    Margo Dydek was a towering Polish professional basketball center renowned as one of the greatest shot-blockers in WNBA history.
  • C. Diana Pokorny
    Diana Pokorny is a film producer best known for her work on the fantasy adventure movie "Inkheart."
  • D. Loralee Czuchna
    Loralee Czuchna is best known as the second wife of American actor and comedian Don Knotts.
  • E. Erika Slezak
    Erika Slezak is an American actress best known for her long-running, acclaimed portrayal of Victoria Lord on the soap opera "One Life to Live."
  • 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 Mikula
Triple: [Rachel Maddow, partner, Susan Mikula]
Generated description
Susan Mikula is an American artist and photographer known for her distinctive, often experimental photographic work and for her long-term relationship with television host Rachel Maddow.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Susan Mikula
Target entity description: Susan Mikula is an American artist and photographer known for her distinctive, often experimental photographic work and for her long-term relationship with television host Rachel Maddow.
  • A. Janine Melnitz
    Janine Melnitz is the Ghostbusters’ sharp-tongued, no-nonsense receptionist who provides comic relief and grounded support to the team.
  • B. Margo Dydek
    Margo Dydek was a towering Polish professional basketball center renowned as one of the greatest shot-blockers in WNBA history.
  • C. Diana Pokorny
    Diana Pokorny is a film producer best known for her work on the fantasy adventure movie "Inkheart."
  • D. Loralee Czuchna
    Loralee Czuchna is best known as the second wife of American actor and comedian Don Knotts.
  • E. Erika Slezak
    Erika Slezak is an American actress best known for her long-running, acclaimed portrayal of Victoria Lord on the soap opera "One Life to Live."
  • 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_69c68857ffc08190857dc62cd5253777 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dbf083b481909dd30e28e908dfdf completed March 27, 2026, 7:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7883f0d988190b170901aea57d360 completed March 28, 2026, 7:50 a.m.
NEDg Description generation batch_69c78a822ab0819097e2b40d4b9e044f completed March 28, 2026, 8 a.m.
NED2 Entity disambiguation (via description) batch_69c78b33f5308190a3f234a2c0bd8b9c completed March 28, 2026, 8:03 a.m.
Created at: March 27, 2026, 2:33 p.m.