Triple
T13988184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unemployment Appeals Commission of Florida |
E336496
|
entity |
| Predicate | reviewLevel |
P67205
|
FINISHED |
| Object | appellate review of unemployment compensation decisions |
—
|
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: appellate review of unemployment compensation decisions | Statement: [Unemployment Appeals Commission of Florida, reviewLevel, appellate review of unemployment compensation decisions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reviewLevel Context triple: [Unemployment Appeals Commission of Florida, reviewLevel, appellate review of unemployment compensation decisions]
-
A.
reviewType
chosen
Indicates the specific category or kind of review associated with an item, action, or relationship.
-
B.
reviewFormat
Indicates the specific structure, style, or medium in which a review is presented or delivered.
-
C.
rating
Indicates an evaluation relationship where one entity assigns a qualitative or quantitative score or judgment to another entity.
-
D.
ratingContext
Indicates the situational or contextual factors under which a rating is given or applies.
-
E.
reviewAggregate
Indicates a summarized evaluation relationship where multiple individual reviews are combined into an overall rating or assessment for an entity.
- 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_69d81c639e808190a0e4b4f3d31c6a59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2ea537408190bb9d35963886803f |
completed | April 14, 2026, 12:10 p.m. |
| PD | Predicate disambiguation | batch_69dd465dfbc4819090d8c61fd572d35f |
completed | April 13, 2026, 7:39 p.m. |
Created at: April 9, 2026, 10:18 p.m.