Triple
T7240596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J.D. Shelley |
E155342
|
entity |
| Predicate | relatedLegalIssue |
P4511
|
FINISHED |
| Object | racial segregation in housing |
—
|
LITERAL FINISHED |
How this triple was built (2 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: racial segregation in housing | Statement: [J.D. Shelley, relatedLegalIssue, racial segregation in housing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedLegalIssue Context triple: [J.D. Shelley, relatedLegalIssue, racial segregation in housing]
-
A.
legalMatters
Indicates that one entity is involved with, concerned about, or responsible for legal issues, processes, or obligations related to another entity or context.
-
B.
relatedLegalConcept
Indicates that one legal concept is connected or associated with another through a relevant legal relationship or context.
-
C.
hasLegalIssue
chosen
Indicates that an entity is involved in, associated with, or subject to a legal problem, dispute, or proceeding.
-
D.
relatedLegalSystem
Indicates that there is an association or connection between two legal systems, such as influence, similarity, shared origin, or mutual relevance.
-
E.
relatedLegalProcess
Indicates that there is an associated legal proceeding or action that is connected to, arises from, or is otherwise relevant to the referenced entity or event.
- F. None of above.
Provenance (3 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_69c688143bfc81908d4176617735e601 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea552a688190a00f5d0ad982f787 |
completed | March 27, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_69c6e7644648819096a5e2de5d0dbe97 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:55 p.m.