Triple

T16523279
Position Surface form Disambiguated ID Type / Status
Subject Hospitality of Abraham mosaic E401372 entity
Predicate featuresCharacter P626 FINISHED
Object Sarah
Sarah is a prominent biblical matriarch, wife of Abraham and mother of Isaac, revered in Jewish, Christian, and Islamic traditions.
E34678 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: [Hospitality of Abraham mosaic, featuresCharacter, Sarah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah
Context triple: [Hospitality of Abraham mosaic, featuresCharacter, 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: [Hospitality of Abraham mosaic, featuresCharacter, Sarah]
Generated description
Sarah is a prominent biblical matriarch, wife of Abraham and mother of Isaac, revered in Jewish, Christian, and Islamic traditions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sarah
Target entity description: Sarah is a prominent biblical matriarch, wife of Abraham and mother of Isaac, revered in Jewish, Christian, and Islamic traditions.
  • A. Sarah chosen
    Sarah is a key matriarch in the Hebrew Bible, revered as the wife of Abraham and mother of Isaac in the Jewish, Christian, and Islamic traditions.
  • 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 Breedlove, better known as Madam C. J. Walker, a pioneering African American entrepreneur and philanthropist in the early 20th century.
  • D. Sarah
    Sarah is a female given name of Hebrew origin, commonly used in English-speaking countries and traditionally meaning "princess."
  • E. Sarah
    Sarah is the given name of Sarah Josepha Hale, a 19th-century American writer and influential editor often credited with helping establish Thanksgiving as a national holiday in the United States.
  • F. None of above.

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_69d883838abc8190bc79cb2d41733ce2 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32ed2622c8190b6429a49ca92284a completed April 18, 2026, 7:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0067a7616c8190af486bef3331e115 completed May 10, 2026, 11:10 a.m.
NEDg Description generation batch_6a006914e0588190afdd0e7c2719696f completed May 10, 2026, 11:16 a.m.
NED2 Entity disambiguation (via description) batch_6a00696d42e081908133fdbee4a301d8 completed May 10, 2026, 11:18 a.m.
Created at: April 10, 2026, 5:14 a.m.