Triple
T8074153
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swann v. Charlotte-Mecklenburg Board of Education |
E188450
|
entity |
| Predicate | parties |
P1790
|
FINISHED |
| Object |
James E. Swann et al.
James E. Swann et al. were the parent plaintiffs who challenged racial segregation in Charlotte, North Carolina’s public schools, leading to a landmark U.S. Supreme Court decision on school desegregation and busing.
|
E710180
|
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: James E. Swann et al. | Statement: [Swann v. Charlotte-Mecklenburg Board of Education, parties, James E. Swann et al.]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: James E. Swann et al. Context triple: [Swann v. Charlotte-Mecklenburg Board of Education, parties, James E. Swann et al.]
-
A.
Tom B. Brown et al.
Tom B. Brown et al. are the research team behind the influential GPT-3 language model paper that significantly advanced large-scale neural language modeling.
-
B.
R. James Blackshire et al.
R. James Blackshire et al. are parties who served as respondents in the U.S. Supreme Court case Village of Arlington Heights v. Metropolitan Housing Development Corp., a landmark decision on housing discrimination and equal protection.
-
C.
Daniel Donnelly et al.
Daniel Donnelly et al. refers to the group of respondents, led by Daniel Donnelly, who were parties challenging a municipal holiday display in the U.S. Supreme Court case Lynch v. Donnelly.
-
D.
J. W. Cumming et al.
J. W. Cumming et al. were the plaintiffs challenging a Georgia county school board’s racially discriminatory education policies in the 1899 U.S. Supreme Court case Cumming v. Richmond County Board of Education.
-
E.
Wurster, Bernardi and Emmons
Wurster, Bernardi and Emmons was a prominent mid-20th-century American architectural firm known for its modernist designs and influential contributions to West Coast architecture.
- 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: James E. Swann et al. Triple: [Swann v. Charlotte-Mecklenburg Board of Education, parties, James E. Swann et al.]
Generated description
James E. Swann et al. were the parent plaintiffs who challenged racial segregation in Charlotte, North Carolina’s public schools, leading to a landmark U.S. Supreme Court decision on school desegregation and busing.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: James E. Swann et al. Target entity description: James E. Swann et al. were the parent plaintiffs who challenged racial segregation in Charlotte, North Carolina’s public schools, leading to a landmark U.S. Supreme Court decision on school desegregation and busing.
-
A.
Tom B. Brown et al.
Tom B. Brown et al. are the research team behind the influential GPT-3 language model paper that significantly advanced large-scale neural language modeling.
-
B.
R. James Blackshire et al.
R. James Blackshire et al. are parties who served as respondents in the U.S. Supreme Court case Village of Arlington Heights v. Metropolitan Housing Development Corp., a landmark decision on housing discrimination and equal protection.
-
C.
Daniel Donnelly et al.
Daniel Donnelly et al. refers to the group of respondents, led by Daniel Donnelly, who were parties challenging a municipal holiday display in the U.S. Supreme Court case Lynch v. Donnelly.
-
D.
J. W. Cumming et al.
J. W. Cumming et al. were the plaintiffs challenging a Georgia county school board’s racially discriminatory education policies in the 1899 U.S. Supreme Court case Cumming v. Richmond County Board of Education.
-
E.
Wurster, Bernardi and Emmons
Wurster, Bernardi and Emmons was a prominent mid-20th-century American architectural firm known for its modernist designs and influential contributions to West Coast architecture.
- 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_69ca82b50c708190863f661d438e68df |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb404a98408190b6c8eecb95ad086d |
completed | March 31, 2026, 3:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc63f000308190a55379f8bf67f0cd |
completed | April 1, 2026, 12:16 a.m. |
| NEDg | Description generation | batch_69cc68634dc88190bc9b9e0598929d4d |
completed | April 1, 2026, 12:35 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc6946aa5481908d682957b818a3e9 |
completed | April 1, 2026, 12:39 a.m. |
Created at: March 30, 2026, 5:27 p.m.