Triple
T186677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Republicans |
E3995
|
entity |
| Predicate | linkedTrend |
P37
|
FINISHED |
| Object | party realignment in the United States |
—
|
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: party realignment in the United States | Statement: [Southern Republicans, linkedTrend, party realignment in the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedTrend Context triple: [Southern Republicans, linkedTrend, party realignment in the United States]
-
A.
relatedTo
chosen
Indicates a general, non-specific relationship or association exists between two entities.
-
B.
popularFor
Indicates that something is widely liked, recognized, or favored specifically because of a particular feature, quality, or use.
-
C.
sharesHead
Indicates that two entities have the same head element, leader, or top-level component in common.
-
D.
sharesHistoryWith
Indicates that two entities have a common or overlapping past, such as shared experiences, events, or origins.
-
E.
mediaMarket
Indicates a relationship where a media outlet or content provider serves, targets, or operates within a particular geographic or demographic market.
- 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_69a25497e2f08190a040f8c6e1842643 |
completed | Feb. 28, 2026, 2:36 a.m. |
| NER | Named-entity recognition | batch_69a2594809288190b3d3b1283e7e0d00 |
completed | Feb. 28, 2026, 2:56 a.m. |
| PD | Predicate disambiguation | batch_69a25670feb081908e26a2543ebe7b3a |
completed | Feb. 28, 2026, 2:44 a.m. |
Created at: Feb. 28, 2026, 2:40 a.m.