Triple
T1931850
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Hammann (DD-412) |
E40961
|
entity |
| Predicate | sunkWhile |
P18834
|
FINISHED |
| Object | alongside USS Yorktown (CV-5) |
—
|
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: alongside USS Yorktown (CV-5) | Statement: [USS Hammann (DD-412), sunkWhile, alongside USS Yorktown (CV-5)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sunkWhile Context triple: [USS Hammann (DD-412), sunkWhile, alongside USS Yorktown (CV-5)]
-
A.
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.
-
B.
sunkBy
Indicates that one entity (typically a vessel or structure) was caused to sink or be destroyed in water by another entity.
-
C.
sunk
Indicates that one entity caused another entity to go below the surface of a liquid, typically water, so that it is submerged or destroyed.
-
D.
torpedoed
Indicates that one entity attacked and struck another entity using a torpedo, typically causing damage or destruction.
-
E.
placeOfSinking
Indicates the location where an object or entity sank or was submerged.
- 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_69a8864711648190b07bed24ed76258e |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb297ec2c819092ad62d72005223d |
completed | March 7, 2026, 5:07 a.m. |
| PD | Predicate disambiguation | batch_69abafeec6f881909d47acb966683279 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:35 p.m.