Triple
T28414206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fourth Battle of Petersburg |
E719750
|
entity |
| Predicate | impactOnLee |
P47033
|
FINISHED |
| Object | reduced Lee’s ability to defend Petersburg |
—
|
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: reduced Lee’s ability to defend Petersburg | Statement: [Fourth Battle of Petersburg, impactOnLee, reduced Lee’s ability to defend Petersburg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: impactOnLee Context triple: [Fourth Battle of Petersburg, impactOnLee, reduced Lee’s ability to defend Petersburg]
-
A.
impactOnLeader
chosen
Indicates that one entity has an effect, influence, or consequence on a leader within a given context.
-
B.
impactStatus
Indicates the current state or condition of how something has affected or influenced a target.
-
C.
impactOnField
Indicates the effect or influence that one entity, action, or development has on a particular field or domain.
-
D.
recognizesImpactOn
Indicates that one entity acknowledges or understands the effect or consequences it has on another entity or situation.
-
E.
impactOnSubject
Indicates the effect, influence, or consequence that one entity, event, or action has on a specified subject.
- 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_69eff6f0f37c8190b37bc6fab08a9449 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 28, 2026, 1:29 a.m.