Triple
T35458888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harris County Jail |
E1024859
|
entity |
| Predicate | typeOfSentenceServed |
P203593
|
FINISHED |
| Object | misdemeanor sentences |
—
|
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: misdemeanor sentences | Statement: [Harris County Jail, typeOfSentenceServed, misdemeanor sentences]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfSentenceServed Context triple: [Harris County Jail, typeOfSentenceServed, misdemeanor sentences]
-
A.
typeOfSentence
Indicates that one sentence is classified as being of a particular type or category (e.g., declarative, interrogative, imperative).
-
B.
typeOfSentenceManaged
Indicates the specific kind or category of sentence that is being handled or controlled in a given context.
-
C.
sentencedTo
Indicates that an authority has officially assigned a specific punishment or penalty to an entity, typically as the outcome of a legal or disciplinary process.
-
D.
sentenceType
Indicates the classification of a sentence according to its communicative function or structural type (e.g., question, statement, command).
-
E.
typicalSentenceType
Indicates the usual or most characteristic type of sentence associated with an entity, such as whether it is typically declarative, interrogative, imperative, or another sentence form.
- 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_69f76df92f108190817222e520e22268 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a01ade363088190b3a3e3dedabd1aa2 |
completed | May 11, 2026, 10:22 a.m. |
| PD | Predicate disambiguation | batch_6a01acf3c5788190932bd8fcf27c123d |
completed | May 11, 2026, 10:18 a.m. |
| PDg | Predicate description generation | batch_6a01ade289a48190b05e51bb6232e0f2 |
completed | May 11, 2026, 10:22 a.m. |
Created at: May 3, 2026, 4:04 p.m.