Triple

T15280579
Position Surface form Disambiguated ID Type / Status
Subject Caroline Aaron E365257 entity
Predicate familyName P18 FINISHED
Object Abady
Abady is the family name of American actress Caroline Aaron, known for her work in film, television, and theater.
 E1148483 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: Abady | Statement: [Caroline Aaron, familyName, Abady]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Abady
Context triple: [Caroline Aaron, familyName, Abady]
  • A. Abodi
    Abodi is the traditional royal title held by the paramount ruler of the Ikale people of southwestern Nigeria.
  • B. Abunayyan
    Abunayyan is a prominent Saudi family name associated with influential figures in business and public life in Saudi Arabia.
  • C. Abyrx
    Abyrx is a medical technology company specializing in biomaterial-based surgical products designed to improve bone repair and hemostasis in operative procedures.
  • D. Adad
    Adad is the Mesopotamian storm and rain god, associated with thunder, fertility, and divine judgment.
  • E. Akhras
    Akhras is a Syrian-origin family name best known for being the maiden surname of Asma al-Assad, the First Lady of Syria.
  • 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: Abady
Triple: [Caroline Aaron, familyName, Abady]
Generated description
Abady is the family name of American actress Caroline Aaron, known for her work in film, television, and theater.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Abady
Target entity description: Abady is the family name of American actress Caroline Aaron, known for her work in film, television, and theater.
  • A. Abodi
    Abodi is the traditional royal title held by the paramount ruler of the Ikale people of southwestern Nigeria.
  • B. Abunayyan
    Abunayyan is a prominent Saudi family name associated with influential figures in business and public life in Saudi Arabia.
  • C. Abyrx
    Abyrx is a medical technology company specializing in biomaterial-based surgical products designed to improve bone repair and hemostasis in operative procedures.
  • D. Adad
    Adad is the Mesopotamian storm and rain god, associated with thunder, fertility, and divine judgment.
  • E. Akhras
    Akhras is a Syrian-origin family name best known for being the maiden surname of Asma al-Assad, the First Lady of Syria.
  • 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_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00e504d8c8190ad6c565a31d1a9bd completed April 15, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69feef754c9c8190abdc1d08fd1511cd completed May 9, 2026, 8:25 a.m.
NEDg Description generation batch_69fef17e1b8481908600e8f2f60ebe98 completed May 9, 2026, 8:34 a.m.
NED2 Entity disambiguation (via description) batch_69fef1e8e41481908f2c8ebe1b1036fa completed May 9, 2026, 8:35 a.m.
Created at: April 10, 2026, 3:15 a.m.