Triple

T14759064
Position Surface form Disambiguated ID Type / Status
Subject Nancy McKeon E346806 entity
Predicate spouse P13 FINISHED
Object Marc Andrus
Marc Andrus is an American film technician and former actor best known as the husband of actress Nancy McKeon.
E1119547 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: Marc Andrus | Statement: [Nancy McKeon, spouse, Marc Andrus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marc Andrus
Context triple: [Nancy McKeon, spouse, Marc Andrus]
  • A. Mark Andrus
    Mark Andrus is an American screenwriter best known for co-writing the acclaimed film "As Good as It Gets."
  • B. Jeff McNeil
    Jeff McNeil is an American professional baseball player, primarily a contact-hitting second baseman and outfielder for the New York Mets known for his high batting average and versatility.
  • C. Michael Moreland
    Michael Moreland is an actor known for appearing in the classic 1950 film "All About Eve."
  • D. Ryne Duren
    Ryne Duren was an American Major League Baseball relief pitcher known for his blazing fastball, poor eyesight, and intimidating wildness on the mound, most notably with the New York Yankees in the late 1950s.
  • E. Brendan Morrow
    Brendan Morrow is a Canadian former professional ice hockey forward best known for his long tenure and captaincy with the NHL’s Dallas Stars.
  • 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: Marc Andrus
Triple: [Nancy McKeon, spouse, Marc Andrus]
Generated description
Marc Andrus is an American film technician and former actor best known as the husband of actress Nancy McKeon.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marc Andrus
Target entity description: Marc Andrus is an American film technician and former actor best known as the husband of actress Nancy McKeon.
  • A. Mark Andrus
    Mark Andrus is an American screenwriter best known for co-writing the acclaimed film "As Good as It Gets."
  • B. Jeff McNeil
    Jeff McNeil is an American professional baseball player, primarily a contact-hitting second baseman and outfielder for the New York Mets known for his high batting average and versatility.
  • C. Michael Moreland
    Michael Moreland is an actor known for appearing in the classic 1950 film "All About Eve."
  • D. Ryne Duren
    Ryne Duren was an American Major League Baseball relief pitcher known for his blazing fastball, poor eyesight, and intimidating wildness on the mound, most notably with the New York Yankees in the late 1950s.
  • E. Brendan Morrow
    Brendan Morrow is a Canadian former professional ice hockey forward best known for his long tenure and captaincy with the NHL’s Dallas Stars.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7f0f5a48190af008352c26574d7 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0cefb7c08190bf69b15165f046d0 completed May 8, 2026, 4:18 p.m.
NEDg Description generation batch_69fe1a0e2820819092abfc2795ba4851 completed May 8, 2026, 5:14 p.m.
NED2 Entity disambiguation (via description) batch_69fe1a89d4d08190a2be8b4b0bc5a472 completed May 8, 2026, 5:16 p.m.
Created at: April 10, 2026, 1:30 a.m.