Triple
T31826323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Broward County Jail system |
E812404
|
entity |
| Predicate | mainIntakeLocation |
P42668
|
FINISHED |
| Object | Broward County Main Jail |
—
|
NE NERFINISHED |
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: Broward County Main Jail | Statement: [Broward County Jail system, mainIntakeLocation, Broward County Main Jail]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainIntakeLocation Context triple: [Broward County Jail system, mainIntakeLocation, Broward County Main Jail]
-
A.
intakeLocation
chosen
Indicates the place or facility where an entity is initially received, admitted, or taken in.
-
B.
mainEntranceLocation
Indicates the location where the primary or main entrance of an entity is situated.
-
C.
mainLocation
Indicates that one entity serves as the primary or central location associated with another entity.
-
D.
primaryIntakeType
Indicates the main or most significant type of intake or input associated with an entity or process.
-
E.
primaryIntake
Indicates that one entity serves as the main or first point of intake, reception, or admission for another 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_69f348e97fa48190aa06286962af6dee |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b21e7e088190832a3db585daea1c |
completed | May 3, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
Created at: April 30, 2026, 11:46 p.m.