Triple
T37857881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sudley Ford |
E944240
|
entity |
| Predicate | crossedByUnit |
P416
|
FINISHED |
| Object | Union Army of Northeastern Virginia |
—
|
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: Union Army of Northeastern Virginia | Statement: [Sudley Ford, crossedByUnit, Union Army of Northeastern Virginia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crossedByUnit Context triple: [Sudley Ford, crossedByUnit, Union Army of Northeastern Virginia]
-
A.
crossedBy
chosen
Indicates that one entity (typically a path, line, or boundary) is intersected or traversed by another entity.
-
B.
crossingOf
Indicates that one entity serves as the intersection or crossing point of two or more linear features, such as roads, paths, or tracks.
-
C.
crossedWith
Indicates that one entity has moved from one side of another entity or boundary to the opposite side, typically by passing over or through it.
-
D.
crossedFrom
Indicates that an entity moved across a boundary or dividing line starting from a specified origin location or side.
-
E.
crossErectedBy
Indicates that a particular cross was constructed, installed, or set up by a specified agent or 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_69f76eee2f9c8190b1272aa2ee55ebf5 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fd389cb28c819099a77e28d25f258a |
completed | May 8, 2026, 1:13 a.m. |
| PD | Predicate disambiguation | batch_69fd3826d8048190ada79a5868d1d7f3 |
completed | May 8, 2026, 1:11 a.m. |
Created at: May 3, 2026, 4:19 p.m.