Triple
T30111006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unionist Party (United States, Civil War era) |
E765273
|
entity |
| Predicate | hadSupportBaseIn |
P60372
|
FINISHED |
| Object | Maryland |
—
|
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: Maryland | Statement: [Unionist Party (United States, Civil War era), hadSupportBaseIn, Maryland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadSupportBaseIn Context triple: [Unionist Party (United States, Civil War era), hadSupportBaseIn, Maryland]
-
A.
hadBase
Indicates that an entity maintained or operated from a particular base location or primary site.
-
B.
hasSupportBaseIn
chosen
Indicates that one entity maintains an operational or organizational base of support located in another entity.
-
C.
hasSupportBase
Indicates that one entity serves as the supporting base or foundation upon which another entity rests, is mounted, or is structurally stabilized.
-
D.
hasBaseOn
Indicates that one entity is supported by, rests upon, or is structurally or conceptually founded on another entity.
-
E.
hasBasedUnit
Indicates that something is defined or measured in terms of a specified base unit.
- 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_69f22475ad7c8190be7f9541044a0bbb |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67dbfc82081909ae5d04676627a6c |
completed | May 2, 2026, 10:42 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:10 p.m.