Triple

T1190527
Position Surface form Disambiguated ID Type / Status
Subject Sandra Day O’Connor E25347 entity
Predicate givenName P17 FINISHED
Object Sandra
Sandra is the given name of Sandra Day O’Connor, the first woman to serve as a Justice on the United States Supreme Court.
 E177157 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: Sandra | Statement: [Sandra Day O’Connor, givenName, Sandra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sandra
Context triple: [Sandra Day O’Connor, givenName, Sandra]
  • A. Paula
    Paula is a feminine given name used in many languages, derived from the Latin name Paulus meaning "small" or "humble."
  • B. Sara
    Sara is a language spoken in parts of Central Africa, particularly in Chad.
  • C. Sara
    Sara is a feminine given name of Hebrew origin meaning "princess," historically borne by notable figures including Sara Ann Delano Roosevelt, the mother of U.S. President Franklin D. Roosevelt.
  • D. Diane
    Diane is a feminine given name of Latin origin, derived from the name of the Roman goddess Diana.
  • E. Marcia
    Marcia was the mother of the Roman emperor Trajan and a member of the provincial Roman aristocracy in Hispania.
  • 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: Sandra
Triple: [Sandra Day O’Connor, givenName, Sandra]
Generated description
Sandra is the given name of Sandra Day O’Connor, the first woman to serve as a Justice on the United States Supreme Court.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sandra
Target entity description: Sandra is the given name of Sandra Day O’Connor, the first woman to serve as a Justice on the United States Supreme Court.
  • A. Paula
    Paula is a feminine given name used in many languages, derived from the Latin name Paulus meaning "small" or "humble."
  • B. Sara
    Sara is a language spoken in parts of Central Africa, particularly in Chad.
  • C. Sara
    Sara is a feminine given name of Hebrew origin meaning "princess," historically borne by notable figures including Sara Ann Delano Roosevelt, the mother of U.S. President Franklin D. Roosevelt.
  • D. Diane
    Diane is a feminine given name of Latin origin, derived from the name of the Roman goddess Diana.
  • E. Marcia
    Marcia was the mother of the Roman emperor Trajan and a member of the provincial Roman aristocracy in Hispania.
  • 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_69a49427d98881908646d6c63b8cea1e completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bd58d8d88190b8d9c9c9de7f4e97 completed March 1, 2026, 10:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad36f482808190b9a999ebbdbabc2e completed March 8, 2026, 8:44 a.m.
NEDg Description generation batch_69ad3812855881909b571d6a7a96d524 completed March 8, 2026, 8:49 a.m.
NED2 Entity disambiguation (via description) batch_69ad38a4017c8190b2c5f1f0d1d9b5a5 completed March 8, 2026, 8:51 a.m.
Created at: March 1, 2026, 7:45 p.m.