Triple
T5643592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Second Battle of Winchester |
E124327
|
entity |
| Predicate | UnionGarrison |
P24784
|
FINISHED |
| Object | Winchester garrison under Robert H. Milroy |
—
|
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: Winchester garrison under Robert H. Milroy | Statement: [Second Battle of Winchester, UnionGarrison, Winchester garrison under Robert H. Milroy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: UnionGarrison Context triple: [Second Battle of Winchester, UnionGarrison, Winchester garrison under Robert H. Milroy]
-
A.
garrisonedUnit
Indicates that one unit is stationed inside, occupying, or defending another entity such as a building, vehicle, or fortification.
-
B.
garrisonedForce
Indicates that a military force is stationed in and occupies a specific location, typically for defense or control.
-
C.
garrisonOrHQ
Indicates that an entity serves as a military garrison or headquarters location for another entity.
-
D.
garrisonOrAssemblyArea
Indicates a location where military forces are stationed, housed, or gathered for organization, preparation, or deployment.
-
E.
garrisonSide
chosen
Indicates the side, faction, or allegiance that a garrison is associated with or belongs to.
- 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_69c00824643c81909ffdb888a2d35189 |
completed | March 22, 2026, 3:17 p.m. |
| NER | Named-entity recognition | batch_69c022a7cd9c819087f86f60e8b65fc3 |
completed | March 22, 2026, 5:11 p.m. |
| PD | Predicate disambiguation | batch_69c01b2168508190b64b355cf50034ad |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:41 p.m.