Triple
T7688941
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Florida Department of State Division of Administrative Hearings |
E174195
|
entity |
| Predicate | hearingOutcome |
P2931
|
FINISHED |
| Object | findings of fact |
—
|
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: findings of fact | Statement: [Florida Department of State Division of Administrative Hearings, hearingOutcome, findings of fact]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hearingOutcome Context triple: [Florida Department of State Division of Administrative Hearings, hearingOutcome, findings of fact]
-
A.
heardByCourt
Indicates that a matter, case, or issue has been formally considered or examined by a court.
-
B.
paroleHearings
Indicates that one or more formal hearings are held to evaluate an incarcerated individual's eligibility or suitability for parole.
-
C.
hearsAppealsBy
Indicates that one party has the authority or role to review and decide on appeals submitted by another party.
-
D.
legalOutcome
chosen
Indicates the resulting legal status, decision, or consequence that follows from a legal process, action, or judgment.
-
E.
heard
Indicates that one entity perceived a sound produced by another entity or source through hearing.
- 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_69c6995966348190939e6c37ba272c06 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c706d1f0208190bc5b695aa5736244 |
completed | March 27, 2026, 10:38 p.m. |
| PD | Predicate disambiguation | batch_69c70163dea88190ae729df50e63dfd7 |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:02 p.m.