Triple
T29847774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of the Kentish Knock |
E757975
|
entity |
| Predicate | dutchCommanderRank |
P47206
|
FINISHED |
| Object | Lieutenant-Admiral |
—
|
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: Lieutenant-Admiral | Statement: [Battle of the Kentish Knock, dutchCommanderRank, Lieutenant-Admiral]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dutchCommanderRank Context triple: [Battle of the Kentish Knock, dutchCommanderRank, Lieutenant-Admiral]
-
A.
DutchCommander
chosen
Indicates that an entity serves as a military commander associated with the Netherlands.
-
B.
germanCommanderRank
Indicates that one entity holds a specific military commander rank within the German armed forces in relation to another entity or context.
-
C.
hasDanishCommanderRank
Indicates that an entity holds or is assigned a military commander rank within the Danish armed forces.
-
D.
commandingOfficerRank
Indicates the military rank held by the officer who has command authority over a given individual or unit.
-
E.
initialCommanderRank
Indicates the military rank an individual held at the time they first assumed a commander position.
- 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_69f2245a82cc8190a387e7d0118d710b |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f6764489c881909618ff635fe6c410 |
completed | May 2, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69f66ec5bf508190ad088b89455252bd |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 29, 2026, 5:42 p.m.