Triple

T20258199
Position Surface form Disambiguated ID Type / Status
Subject Ali MacGraw E498758 entity
Predicate spouse P13 FINISHED
Object Robin Hoen
Robin Hoen is an American investment banker best known as the first husband of actress Ali MacGraw.
E1420555 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: Robin Hoen | Statement: [Ali MacGraw, spouse, Robin Hoen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robin Hoen
Context triple: [Ali MacGraw, spouse, Robin Hoen]
  • A. Ian Gelder
    Ian Gelder is a British actor best known for his work in television, film, and theatre, including roles in high-profile series such as Game of Thrones.
  • B. Mark VanHaren
    Mark VanHaren is an entrepreneur best known as the founder of the company Architext.
  • C. Mark VanHaren
    Mark VanHaren is an entrepreneur best known as a founder of the early internet portal and search company Excite.
  • D. Eric Marienthal
    Eric Marienthal is an American contemporary jazz saxophonist known for his work in jazz fusion and smooth jazz, including prominent collaborations with leading artists and bands.
  • E. David Oelhoffen
    David Oelhoffen is a French film director and screenwriter known for his character-driven dramas and literary adaptations.
  • 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: Robin Hoen
Triple: [Ali MacGraw, spouse, Robin Hoen]
Generated description
Robin Hoen is an American investment banker best known as the first husband of actress Ali MacGraw.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Robin Hoen
Target entity description: Robin Hoen is an American investment banker best known as the first husband of actress Ali MacGraw.
  • A. Ian Gelder
    Ian Gelder is a British actor best known for his work in television, film, and theatre, including roles in high-profile series such as Game of Thrones.
  • B. Mark VanHaren
    Mark VanHaren is an entrepreneur best known as the founder of the company Architext.
  • C. Mark VanHaren
    Mark VanHaren is an entrepreneur best known as a founder of the early internet portal and search company Excite.
  • D. Eric Marienthal
    Eric Marienthal is an American contemporary jazz saxophonist known for his work in jazz fusion and smooth jazz, including prominent collaborations with leading artists and bands.
  • E. David Oelhoffen
    David Oelhoffen is a French film director and screenwriter known for his character-driven dramas and literary adaptations.
  • 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_69da6275fa6c8190952924930adee150 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e674c7296c819092860942de8f28d5 completed April 20, 2026, 6:47 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08552c65488190922fc54374072e69 completed May 16, 2026, 11:29 a.m.
NEDg Description generation batch_6a0855d7d87481908ff14d53a2ac94f7 completed May 16, 2026, 11:32 a.m.
NED2 Entity disambiguation (via description) batch_6a0856e66c808190b5ef994f1cbc5f3e completed May 16, 2026, 11:37 a.m.
Created at: April 11, 2026, 11:41 p.m.