Triple
T27726062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Dunedin |
E699098
|
entity |
| Predicate | sinkingWar |
P18834
|
FINISHED |
| Object | World War II |
—
|
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: World War II | Statement: [HMS Dunedin, sinkingWar, World War II]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sinkingWar Context triple: [HMS Dunedin, sinkingWar, World War II]
-
A.
sinkingConflict
Indicates a situation where one entity’s decline, failure, or deterioration creates or intensifies a conflict with another entity.
-
B.
sunkBy
Indicates that one entity (typically a vessel or structure) was caused to sink or be destroyed in water by another entity.
-
C.
sunkDuring
chosen
Indicates that one entity was sunk in the course of, or as a result of, the event or time period represented by another entity.
-
D.
sunkOff
Indicates that one entity was sunk at a location situated off (near but not directly at) another referenced place or feature.
-
E.
shipAttacked
Indicates that one ship has carried out an attack against another ship.
- 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_69ef591012dc8190a6f1ec994f9f7ff7 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f6364042dc8190a2dc2133ec220baa |
completed | May 2, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69f63188e7408190af8ce8b93d128c63 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 3:09 p.m.