Triple

T10604478
Position Surface form Disambiguated ID Type / Status
Subject Anna Gunn E275836 entity
Predicate televisionRole P1668 FINISHED
Object Martha Bullock
Martha Bullock is a fictional character from the television series "Deadwood," known as the refined and resilient wife of lawman Seth Bullock.
E928136 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: Martha Bullock | Statement: [Anna Gunn, televisionRole, Martha Bullock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martha Bullock
Context triple: [Anna Gunn, televisionRole, Martha Bullock]
  • A. Mary Bullock
    Mary Bullock was the wife of Amos Kendall, a prominent 19th-century American journalist, politician, and U.S. Postmaster General.
  • B. Martha McMillan Roberts
    Martha McMillan Roberts was a Farm Security Administration photographer known for documenting American life during the Great Depression era.
  • C. Marion Nelson
    Marion Nelson is a screenwriter known for writing the screenplay for the film "Tracks."
  • D. Susan Holbert McDaniel
    Susan Holbert McDaniel was the mother of pioneering African American actress Hattie McDaniel, the first Black performer to win an Academy Award.
  • E. Mary Little
    Mary Little is a family member of Earl Little, known primarily through her relation to him.
  • 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: Martha Bullock
Triple: [Anna Gunn, televisionRole, Martha Bullock]
Generated description
Martha Bullock is a fictional character from the television series "Deadwood," known as the refined and resilient wife of lawman Seth Bullock.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Martha Bullock
Target entity description: Martha Bullock is a fictional character from the television series "Deadwood," known as the refined and resilient wife of lawman Seth Bullock.
  • A. Mary Bullock
    Mary Bullock was the wife of Amos Kendall, a prominent 19th-century American journalist, politician, and U.S. Postmaster General.
  • B. Martha McMillan Roberts
    Martha McMillan Roberts was a Farm Security Administration photographer known for documenting American life during the Great Depression era.
  • C. Marion Nelson
    Marion Nelson is a screenwriter known for writing the screenplay for the film "Tracks."
  • D. Susan Holbert McDaniel
    Susan Holbert McDaniel was the mother of pioneering African American actress Hattie McDaniel, the first Black performer to win an Academy Award.
  • E. Mary Little
    Mary Little is a family member of Earl Little, known primarily through her relation to him.
  • 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_69d6aaf948d88190806cc3a8c47a3fb2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d6df4992248190b640d743ccf02c82 completed April 8, 2026, 11:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69e6035cf86081909603cec9aa5bd9d6 completed April 20, 2026, 10:43 a.m.
NEDg Description generation batch_69e610a07bf881908de79850edb9576f completed April 20, 2026, 11:40 a.m.
NED2 Entity disambiguation (via description) batch_69e617fdaaa88190a1860fb00309596b completed April 20, 2026, 12:11 p.m.
Created at: April 8, 2026, 7:32 p.m.