Triple
T10538817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Frayser’s Farm |
E248640
|
entity |
| Predicate | opponentAction |
P67175
|
FINISHED |
| Object | Confederate forces attacked retreating Union troops |
—
|
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: Confederate forces attacked retreating Union troops | Statement: [Battle of Frayser’s Farm, opponentAction, Confederate forces attacked retreating Union troops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opponentAction Context triple: [Battle of Frayser’s Farm, opponentAction, Confederate forces attacked retreating Union troops]
-
A.
opponentActionEnded
Indicates that an opposing party’s action or move has been completed or has come to an end.
-
B.
opponentStrategy
Indicates that one entity employs or represents a strategic plan specifically designed to counter or compete against another entity.
-
C.
opponentState
Indicates the condition or status that an opposing party or competitor is currently in within a given context or interaction.
-
D.
hasOpponentAction
chosen
Indicates that one entity performs an action that is in opposition or direct competition to the action of another entity.
-
E.
opponentInCase
Indicates that two parties are on opposing sides in the same legal case or proceeding.
- 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_69d381c5c7448190bec34bee7ec72bac |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50a5730d88190b266a940faf53f65 |
completed | April 7, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69d4fb9729288190a0149f127acd7ae3 |
completed | April 7, 2026, 12:41 p.m. |
Created at: April 6, 2026, 12:31 p.m.