Triple
T10822826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Battle of Kernstown |
E255417
|
entity |
| Predicate | JacksonApproximateStrength |
P83926
|
FINISHED |
| Object | about 3,800–4,200 men |
—
|
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: about 3,800–4,200 men | Statement: [First Battle of Kernstown, JacksonApproximateStrength, about 3,800–4,200 men]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: JacksonApproximateStrength Context triple: [First Battle of Kernstown, JacksonApproximateStrength, about 3,800–4,200 men]
-
A.
teamStrength
Indicates the comparative overall capability or power level of a team, often used to assess how strong one team is relative to others.
-
B.
opponentStrength
Indicates the level or degree of power, skill, or capability possessed by an opposing party in a competitive or adversarial context.
-
C.
approximateEnemyStrength
chosen
Indicates estimating the opposing side’s combat capabilities or power level, typically based on available but potentially incomplete information.
-
D.
powerRating
Indicates the level or amount of power associated with an entity, typically expressing its strength, capacity, or performance capability.
-
E.
estimatedStrength
Indicates that a value represents an approximate or inferred level, magnitude, or intensity of something rather than a precisely measured strength.
- 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_69d6aa8081448190a9324184f2bd1c26 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7344c551c8190a7491d468b8a4a04 |
completed | April 9, 2026, 5:08 a.m. |
| PD | Predicate disambiguation | batch_69d70d1bf3648190b36fa96ea018e0dc |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:18 p.m.