Triple

T15979191
Position Surface form Disambiguated ID Type / Status
Subject Sarah Thompson, Countess Rumford E387527 entity
Predicate givenName P17 FINISHED
Object Sarah
Sarah is the given name of Sarah Thompson, Countess Rumford, an 18th–19th century noblewoman known for her association with the scientist and inventor Benjamin Thompson (Count Rumford).
E1188743 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 | Statement: [Sarah Thompson, Countess Rumford, givenName, Sarah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah
Context triple: [Sarah Thompson, Countess Rumford, givenName, Sarah]
  • A. Sarah
    Sarah is the central protagonist of the story "Horse Girl," around whom the main narrative and character development revolve.
  • B. Sarah
    Sarah is a person whose full name is Sarah Catherine McPherson Risher Getty.
  • C. Sarah
    Sarah is the given name of Sarah P. Duke, the philanthropist and namesake of Duke University's Sarah P. Duke Gardens.
  • D. Sarah
    Sarah is the given name of the renowned 19th- and early 20th-century French stage actress Sarah Bernhardt, often called "the Divine Sarah."
  • E. Sarah
    Sarah Onyango Obama was the Kenyan educator and philanthropist best known as the step-grandmother of former U.S. President Barack Obama.
  • 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
Triple: [Sarah Thompson, Countess Rumford, givenName, Sarah]
Generated description
Sarah is the given name of Sarah Thompson, Countess Rumford, an 18th–19th century noblewoman known for her association with the scientist and inventor Benjamin Thompson (Count Rumford).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sarah
Target entity description: Sarah is the given name of Sarah Thompson, Countess Rumford, an 18th–19th century noblewoman known for her association with the scientist and inventor Benjamin Thompson (Count Rumford).
  • A. Sarah
    Sarah is the given name of Lady Sarah Cadogan, an English noblewoman from the early 18th century.
  • B. Sarah
    Sarah is the given name of Sarah Moore Grimké, a prominent 19th-century American abolitionist, women's rights advocate, and writer.
  • C. Sarah
    Sarah is the given name of Sarah Jane Negley Mellon, a prominent American socialite and philanthropist from the influential Mellon family.
  • D. Sarah
    Sarah is the given name of Sarah Breedlove, better known as Madam C. J. Walker, a pioneering African American entrepreneur and philanthropist in the early 20th century.
  • E. Sarah
    Sarah is the given name of Lady Sarah Chatto, a British painter and member of the extended royal family.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1575362e081909ff36e4d3c15ff2f completed April 16, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3c9567c8190af87c3fcf8a4af15 completed May 9, 2026, 11:31 p.m.
NEDg Description generation batch_69ffc7fb8f308190b649a64c344884b0 completed May 9, 2026, 11:49 p.m.
NED2 Entity disambiguation (via description) batch_69ffc83b4c648190bce41afbd6547fc1 completed May 9, 2026, 11:50 p.m.
Created at: April 10, 2026, 4:54 a.m.