Triple

T6871376
Position Surface form Disambiguated ID Type / Status
Subject Mary Crosby E158553 entity
Predicate spouse P13 FINISHED
Object Mark Brodka
Mark Brodka is an American attorney best known as the husband of actress Mary Crosby.
 E625426 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: Mark Brodka | Statement: [Mary Crosby, spouse, Mark Brodka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mark Brodka
Context triple: [Mary Crosby, spouse, Mark Brodka]
  • A. Andrew Goczkowski
    Andrew Goczkowski is an American local government leader serving as the mayor of Des Plaines, Illinois.
  • B. Mark Czyzewski
    Mark Czyzewski is an editor known for his work on the film "Greyhound."
  • C. Andrew Bryniarski
    Andrew Bryniarski is an American actor and former bodybuilder best known for playing imposing, physically intimidating characters in films such as The Texas Chainsaw Massacre (2003) and its prequel.
  • D. David Burtka
    David Burtka is an American actor and professional chef known for his work on stage and screen and for his long-term relationship and marriage to Neil Patrick Harris.
  • E. Matt Kolodzik
    Matt Kolodzik is an American wrestler best known as a multiple-time All-American standout for Princeton University's wrestling program.
  • 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: Mark Brodka
Triple: [Mary Crosby, spouse, Mark Brodka]
Generated description
Mark Brodka is an American attorney best known as the husband of actress Mary Crosby.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mark Brodka
Target entity description: Mark Brodka is an American attorney best known as the husband of actress Mary Crosby.
  • A. Andrew Goczkowski
    Andrew Goczkowski is an American local government leader serving as the mayor of Des Plaines, Illinois.
  • B. Mark Czyzewski
    Mark Czyzewski is an editor known for his work on the film "Greyhound."
  • C. Andrew Bryniarski
    Andrew Bryniarski is an American actor and former bodybuilder best known for playing imposing, physically intimidating characters in films such as The Texas Chainsaw Massacre (2003) and its prequel.
  • D. David Burtka
    David Burtka is an American actor and professional chef known for his work on stage and screen and for his long-term relationship and marriage to Neil Patrick Harris.
  • E. Matt Kolodzik
    Matt Kolodzik is an American wrestler best known as a multiple-time All-American standout for Princeton University's wrestling program.
  • 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_69c68831e3648190a643c328122e4d43 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d8ac04e08190aa8011c0ade9d509 completed March 27, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c742a841548190abd706ea1efd622f completed March 28, 2026, 2:53 a.m.
NEDg Description generation batch_69c743a639f88190a0758194433322bf completed March 28, 2026, 2:57 a.m.
NED2 Entity disambiguation (via description) batch_69c7445fbd488190938ec3dd59cbeb2c completed March 28, 2026, 3 a.m.
Created at: March 27, 2026, 2:22 p.m.