Triple

T13400324
Position Surface form Disambiguated ID Type / Status
Subject Stefan Holt E319809 entity
Predicate spouse P13 FINISHED
Object Morgan Holt
Morgan Holt is the wife of American television news anchor Stefan Holt.
E1044793 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: Morgan Holt | Statement: [Stefan Holt, spouse, Morgan Holt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Morgan Holt
Context triple: [Stefan Holt, spouse, Morgan Holt]
  • A. Morgan Hess
    Morgan Hess is a central character in the 2002 science fiction thriller film "Signs," portrayed as the young son of former priest Graham Hess.
  • B. Morgan Hart
    Morgan Hart is an American actress best known for her work in television and for being married to actor Don Most.
  • C. Morgan Saylor
    Morgan Saylor is an American actress best known for her role as Dana Brody on the television series "Homeland" and for appearances in films such as "McFarland, USA."
  • D. Morgan Henderson
    Morgan Henderson is an American multi-instrumentalist and composer best known as a member of the indie folk band Fleet Foxes and for his work with various experimental and rock projects.
  • E. Morgan Hentz
    Morgan Hentz is an American volleyball libero best known for her standout collegiate career at Stanford University, where she became one of the top defensive players in the nation.
  • 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: Morgan Holt
Triple: [Stefan Holt, spouse, Morgan Holt]
Generated description
Morgan Holt is the wife of American television news anchor Stefan Holt.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Morgan Holt
Target entity description: Morgan Holt is the wife of American television news anchor Stefan Holt.
  • A. Morgan Hess
    Morgan Hess is a central character in the 2002 science fiction thriller film "Signs," portrayed as the young son of former priest Graham Hess.
  • B. Morgan Hart
    Morgan Hart is an American actress best known for her work in television and for being married to actor Don Most.
  • C. Morgan Saylor
    Morgan Saylor is an American actress best known for her role as Dana Brody on the television series "Homeland" and for appearances in films such as "McFarland, USA."
  • D. Morgan Henderson
    Morgan Henderson is an American multi-instrumentalist and composer best known as a member of the indie folk band Fleet Foxes and for his work with various experimental and rock projects.
  • E. Morgan Hentz
    Morgan Hentz is an American volleyball libero best known for her standout collegiate career at Stanford University, where she became one of the top defensive players in the nation.
  • 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_69d806b943cc8190b6af624d385d7e12 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbae47e99081909d8b5dba97a11988 completed April 12, 2026, 2:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75475d7648190b050e44a5312d13d completed May 3, 2026, 1:58 p.m.
NEDg Description generation batch_69f75681f6b4819088b1d906b338e8f2 completed May 3, 2026, 2:06 p.m.
NED2 Entity disambiguation (via description) batch_69f756d02214819084fe971ead168b1a completed May 3, 2026, 2:08 p.m.
Created at: April 9, 2026, 9:34 p.m.