Triple
T4268394
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heman Marion Sweatt |
E96879
|
entity |
| Predicate | legalCaseYear |
P29330
|
FINISHED |
| Object | 1950 |
—
|
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: 1950 | Statement: [Heman Marion Sweatt, legalCaseYear, 1950]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalCaseYear Context triple: [Heman Marion Sweatt, legalCaseYear, 1950]
-
A.
yearFiled
Indicates the specific calendar year in which a document, case, application, or record was officially filed.
-
B.
legalCase
Indicates a relationship where a formal legal dispute or proceeding exists between parties, typically adjudicated by a court or similar authority.
-
C.
limitedByCourtCaseYear
Indicates that the applicability or validity of something is constrained or restricted based on the year of a specific court case.
-
D.
legalCaseAlongside
Indicates that two or more legal cases are proceeding in parallel or in coordination, such that they are related or handled together in some aspect of the legal process.
-
E.
trialYear
chosen
Indicates the calendar year in which a particular trial takes place or is conducted.
- 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_69b34543f06c8190915ebb1a4574ffa9 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34ff913608190b6ccf4a85057b07b |
completed | March 12, 2026, 11:44 p.m. |
| PD | Predicate disambiguation | batch_69b347f8dcb08190a725c1f7fb5a7466 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:07 p.m.