Triple
T20805690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ray Nagin |
E512146
|
entity |
| Predicate | sentenceDuration |
P141893
|
FINISHED |
| Object | 10 years in federal prison |
—
|
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: 10 years in federal prison | Statement: [Ray Nagin, sentenceDuration, 10 years in federal prison]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sentenceDuration Context triple: [Ray Nagin, sentenceDuration, 10 years in federal prison]
-
A.
sentenceLength
Indicates the length or number of units (such as characters, words, or tokens) that a given sentence contains.
-
B.
lengthInSeconds
Indicates that one entity specifies the duration of another entity measured in seconds.
-
C.
timeToSentence
Indicates the amount of time that elapses from a relevant starting point (e.g., offense, arrest, or charge) until a formal sentence is imposed.
-
D.
lengthInMinutes
Indicates the duration of something expressed as a number of minutes.
-
E.
recordDuration
Indicates the length of time for which something is recorded or captured.
- F. None of above. chosen
Provenance (4 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_69e0b4cc69f481908e98751e697b9df4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2cf1cbc819092d92625dfb107d0 |
completed | April 21, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69e5c99ca55481908e8d434fa901cfd6 |
completed | April 20, 2026, 6:37 a.m. |
| PDg | Predicate description generation | batch_69e5d53c4d6881909b4d0a716fa5ed4a |
completed | April 20, 2026, 7:26 a.m. |
Created at: April 16, 2026, 12:40 p.m.