Triple

T7025380
Position Surface form Disambiguated ID Type / Status
Subject Esther Drummond E162931 entity
Predicate hasRelative P367 FINISHED
Object Sarah Drummond
Sarah Drummond is a relative of Esther Drummond, known primarily through this family connection.
E636840 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: Sarah Drummond | Statement: [Esther Drummond, hasRelative, Sarah Drummond]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Drummond
Context triple: [Esther Drummond, hasRelative, Sarah Drummond]
  • A. Elizabeth Davis
    Elizabeth Davis is an American academic leader and administrator who serves as the president of Furman University.
  • B. Elizabeth Eldridge
    Elizabeth Eldridge was the wife of Salem Village minister Samuel Parris, associated with the period of the Salem witch trials in late 17th-century Massachusetts.
  • C. Elizabeth Grove
    Elizabeth Grove is a residential suburb in the northern Adelaide metropolitan area of South Australia.
  • D. Elizabeth Fairfax
    Elizabeth Fairfax is a member of the Fairfax family, historically associated with the British aristocracy and landed gentry.
  • E. Emily Rutherfurd
    Emily Rutherfurd is an American actress best known for her comedic television roles, including a prominent part on the sitcom "The New Adventures of Old Christine."
  • 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: Sarah Drummond
Triple: [Esther Drummond, hasRelative, Sarah Drummond]
Generated description
Sarah Drummond is a relative of Esther Drummond, known primarily through this family connection.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sarah Drummond
Target entity description: Sarah Drummond is a relative of Esther Drummond, known primarily through this family connection.
  • A. Elizabeth Davis
    Elizabeth Davis is an American academic leader and administrator who serves as the president of Furman University.
  • B. Elizabeth Eldridge
    Elizabeth Eldridge was the wife of Salem Village minister Samuel Parris, associated with the period of the Salem witch trials in late 17th-century Massachusetts.
  • C. Elizabeth Grove
    Elizabeth Grove is a residential suburb in the northern Adelaide metropolitan area of South Australia.
  • D. Elizabeth Fairfax
    Elizabeth Fairfax is a member of the Fairfax family, historically associated with the British aristocracy and landed gentry.
  • E. Emily Rutherfurd
    Emily Rutherfurd is an American actress best known for her comedic television roles, including a prominent part on the sitcom "The New Adventures of Old Christine."
  • 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_69c6885b26248190a857541e3d10e299 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e1fb8f0c8190b15dd7ce7ab6a8f2 completed March 27, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c77581e2a88190ad2ec9855772c6a5 completed March 28, 2026, 6:30 a.m.
NEDg Description generation batch_69c7768f12648190a8e9855af2458a94 completed March 28, 2026, 6:34 a.m.
NED2 Entity disambiguation (via description) batch_69c776bdf56c8190a9fa83d6f2697f1b completed March 28, 2026, 6:35 a.m.
Created at: March 27, 2026, 2:35 p.m.