Triple
T21020306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Cherbourg |
E517786
|
entity |
| Predicate | opposingCommanderUnion |
P1698
|
FINISHED |
| Object | John A. Winslow |
—
|
NE NERFINISHED |
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: John A. Winslow | Statement: [Battle of Cherbourg, opposingCommanderUnion, John A. Winslow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opposingCommanderUnion Context triple: [Battle of Cherbourg, opposingCommanderUnion, John A. Winslow]
-
A.
opposingCommander
chosen
Indicates that one entity serves as the commanding officer of a force that is in opposition or conflict with the force commanded by another entity.
-
B.
opposingCommanderSide
Indicates that one commander is on the opposing or enemy side relative to another commander in a conflict or confrontation.
-
C.
primaryOpposingCommanderUS
Indicates that the referenced person is the main opposing military commander of the United States in a given conflict or operation.
-
D.
opposingAlliance
Indicates that two entities belong to rival or mutually opposed alliances or factions.
-
E.
commandersSide
Indicates that one entity is on the same side, faction, or team as the commander in a conflict or competitive context.
- 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_69e0b50262b081909bc488937145eb73 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc5c905c8190ba2f9f82b6cd1648 |
completed | April 21, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf274ac81909bbf245627dc8fdc |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:54 p.m.