Triple
T24282173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reagan-Bush campaign |
E605571
|
entity |
| Predicate | regionStrength |
P155681
|
FINISHED |
| Object | American South |
—
|
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: American South | Statement: [Reagan-Bush campaign, regionStrength, American South]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionStrength Context triple: [Reagan-Bush campaign, regionStrength, American South]
-
A.
sectorStrength
Indicates the relative performance or influence level of a specific sector compared to others within a broader system or market.
-
B.
stateLevelStrength
Indicates the degree of power, capacity, or effectiveness that a state-level entity possesses in performing its functions or exerting influence.
-
C.
regionRankContext
Indicates the relative ranking or position of something within a specific geographic or regional context.
-
D.
regionComparedTo
Indicates a comparative relationship between two regions, specifying how one region differs from or relates to the other along a particular dimension (e.g., size, value, or status).
-
E.
regionType
Indicates the classification or category of a region, specifying what kind of region it is (e.g., administrative, geographic, or functional).
- 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_69e295480d0c8190846fc3c2e2da1d4c |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28f52e57c8190ab73e4b2b6a9eafd |
completed | April 29, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69f1c457a2908190993824395b3c365d |
completed | April 29, 2026, 8:41 a.m. |
| PDg | Predicate description generation | batch_69f27a753ca8819095706970d368f762 |
completed | April 29, 2026, 9:39 p.m. |
Created at: April 18, 2026, 12:08 a.m.