Triple

T3908412
Position Surface form Disambiguated ID Type / Status
Subject Jason Robards E87261 entity
Predicate spouse P13 FINISHED
Object Rachel Taylor
Rachel Taylor was the second wife of acclaimed American actor Jason Robards, with whom she was married in the mid-20th century.
 E397289 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: Rachel Taylor | Statement: [Jason Robards, spouse, Rachel Taylor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rachel Taylor
Context triple: [Jason Robards, spouse, Rachel Taylor]
  • A. Rachael Taylor
    Rachael Taylor is an Australian actress known for her roles in films like "Transformers" and TV series such as "Jessica Jones."
  • B. Lee Taylor
    Lee Taylor is a fictional character appearing in the "Doctor X" universe.
  • C. Teresa Palmer
    Teresa Palmer is an Australian actress known for her roles in films such as "Warm Bodies," "Lights Out," and "Hacksaw Ridge."
  • D. Sarah Jennings
    Sarah Jennings, later known as Sarah Churchill, Duchess of Marlborough, was a powerful English courtier and close confidante of Queen Anne who became one of the most influential women in early 18th-century British politics.
  • E. Lindsay Duncan
    Lindsay Duncan is a Scottish actress acclaimed for her work on stage, film, and television, known for roles in productions such as "About Time," "Rome," and "Doctor Who."
  • 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: Rachel Taylor
Triple: [Jason Robards, spouse, Rachel Taylor]
Generated description
Rachel Taylor was the second wife of acclaimed American actor Jason Robards, with whom she was married in the mid-20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rachel Taylor
Target entity description: Rachel Taylor was the second wife of acclaimed American actor Jason Robards, with whom she was married in the mid-20th century.
  • A. Rachael Taylor
    Rachael Taylor is an Australian actress known for her roles in films like "Transformers" and TV series such as "Jessica Jones."
  • B. Lee Taylor
    Lee Taylor is a fictional character appearing in the "Doctor X" universe.
  • C. Teresa Palmer
    Teresa Palmer is an Australian actress known for her roles in films such as "Warm Bodies," "Lights Out," and "Hacksaw Ridge."
  • D. Sarah Jennings
    Sarah Jennings, later known as Sarah Churchill, Duchess of Marlborough, was a powerful English courtier and close confidante of Queen Anne who became one of the most influential women in early 18th-century British politics.
  • E. Lindsay Duncan
    Lindsay Duncan is a Scottish actress acclaimed for her work on stage, film, and television, known for roles in productions such as "About Time," "Rome," and "Doctor Who."
  • 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_69aed9424514819086e9c58adde6652d completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeed13bb14819096842c6c82342524 completed March 9, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b51caf41c881909c5156480b46e794 completed March 14, 2026, 8:30 a.m.
NEDg Description generation batch_69b51dab33488190b8e09ec26251a469 completed March 14, 2026, 8:34 a.m.
NED2 Entity disambiguation (via description) batch_69b51e0e9df08190959bc5cb7084d8a5 completed March 14, 2026, 8:36 a.m.
Created at: March 9, 2026, 3:22 p.m.