Triple
T1154037
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | First Battle of Bull Run |
E23741
|
entity |
| Predicate | woundedApproximate |
P661
|
FINISHED |
| Object | about 1,100 Union soldiers wounded |
—
|
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 1,100 Union soldiers wounded | Statement: [First Battle of Bull Run, woundedApproximate, about 1,100 Union soldiers wounded]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: woundedApproximate Context triple: [First Battle of Bull Run, woundedApproximate, about 1,100 Union soldiers wounded]
-
A.
approximates
Indicates that one entity is close to, but not exactly equal to, the value, form, or behavior of another entity.
-
B.
casualtiesEstimate
chosen
Indicates an estimated number of people killed, injured, or otherwise harmed as a result of an event or incident.
-
C.
approximateMass
Indicates that one entity has a mass value that is an estimate or close approximation of the mass of another entity.
-
D.
hasDimensionsApprox
Indicates that an entity has physical dimensions that are known only approximately, rather than as exact measurements.
-
E.
approximateRadius
Indicates that one entity specifies or provides an estimated value for the radius of another 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_69a493f0d32c8190ac74bad3c87f2641 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bc8e9cb481908a528a828b21d497 |
completed | March 1, 2026, 10:24 p.m. |
| PD | Predicate disambiguation | batch_69a4bb50d19c81908a98dbbb04a8906f |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:44 p.m.