Triple
T28288551
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bamberg County |
E713355
|
entity |
| Predicate | regionWithinState |
P69120
|
FINISHED |
| Object | southern South Carolina |
—
|
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: southern South Carolina | Statement: [Bamberg County, regionWithinState, southern South Carolina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionWithinState Context triple: [Bamberg County, regionWithinState, southern South Carolina]
-
A.
regionalLocationWithinState
chosen
Indicates that one region is geographically located within the boundaries of a specific state.
-
B.
regionOfState
Indicates that one administrative or geographical region is a subdivision or part of a larger state.
-
C.
stateGovernedWithin
Indicates that one state exercises governmental authority or control within the territorial or jurisdictional boundaries of another state.
-
D.
locatedInStateOrRegion
Indicates that one entity is geographically situated within the boundaries of a specified state or region.
-
E.
regionWithinUSCCB
Indicates that one region is located within or falls under the jurisdiction of a specified USCCB (United States Conference of Catholic Bishops) region.
- 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_69efb52371d88190a1381c4e58a3b731 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69fcef654d588190b29ecc76678d1aa0 |
completed | May 7, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69fcecdb97f48190b382b7d13be92dc0 |
completed | May 7, 2026, 7:49 p.m. |
Created at: April 27, 2026, 11:27 p.m.