Triple
T4271843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Francisco Sheriff’s Office |
E96957
|
entity |
| Predicate | typeOfDetentionFacilities |
P50528
|
FINISHED |
| Object | county jails |
—
|
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: county jails | Statement: [San Francisco Sheriff’s Office, typeOfDetentionFacilities, county jails]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfDetentionFacilities Context triple: [San Francisco Sheriff’s Office, typeOfDetentionFacilities, county jails]
-
A.
detentionType
chosen
Indicates the specific category or form of detention applied to an entity within a custodial or restrictive context.
-
B.
placeOfDetention
Indicates the location or facility where an entity is or was held in detention.
-
C.
prisonType
Indicates the specific category or classification of a prison associated with an entity.
-
D.
detaineeStatus
Indicates the current legal or custodial condition of a person being detained, such as whether they are in custody, released, or under a specific detention regime.
-
E.
detentionCondition
Indicates the specific terms, circumstances, or requirements under which a person is held in detention.
- 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_69b34ffce3d8819083d2278547fa52c1 |
completed | March 12, 2026, 11:45 p.m. |
| PD | Predicate disambiguation | batch_69b347faa45481908c19c29fb906dc92 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:07 p.m.