Triple
T20976576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HNoMS Helge Ingstad |
E516640
|
entity |
| Predicate | salvage |
P47246
|
FINISHED |
| Object | refloated in 2019 |
—
|
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: refloated in 2019 | Statement: [HNoMS Helge Ingstad, salvage, refloated in 2019]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: salvage Context triple: [HNoMS Helge Ingstad, salvage, refloated in 2019]
-
A.
wreckSalvaged
chosen
Indicates that a previously wrecked object or structure has been recovered or salvaged from its damaged or sunken state.
-
B.
scavenges
Indicates that one entity searches through and collects discarded or leftover resources from another entity or environment for its own use.
-
C.
revival
Indicates the act of bringing something back into use, popularity, or active existence after a period of decline, dormancy, or disuse.
-
D.
save
Indicates preserving or storing something from loss, harm, or use, often for future benefit or protection.
-
E.
recovery
Indicates the process or state in which an entity regains a previous condition, function, or status after loss, damage, or decline.
- 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_69e0b4fee5ac8190875fa9ceba1a5e5e |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fba4a0dc819083b90795d26adfff |
completed | April 21, 2026, 4:23 a.m. |
| PD | Predicate disambiguation | batch_69e5dbe6976081908abd4e9c8734bae9 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:47 p.m.