Triple
T30867961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yankee-class submarine |
E786254
|
entity |
| Predicate | K-219IncidentOutcome |
P171318
|
FINISHED |
| Object | loss of submarine |
—
|
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: loss of submarine | Statement: [Yankee-class submarine, K-219IncidentOutcome, loss of submarine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: K-219IncidentOutcome Context triple: [Yankee-class submarine, K-219IncidentOutcome, loss of submarine]
-
A.
K-219IncidentYear
Indicates the year in which the K-219 incident occurred.
-
B.
K-219IncidentLocation
Indicates the location where the K-219 incident took place or occurred.
-
C.
scuttledAfter
Indicates that one entity was deliberately sunk or rendered inoperable after the occurrence or completion of another specified event or action.
-
D.
locationOfKamikazeAttack
Indicates the place where a kamikaze attack occurred or was carried out.
-
E.
statusOfTirpitzAfterOperation
Indicates the condition or state of the Tirpitz following the specified military operation.
- F. None of above. chosen
Provenance (4 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_69f224b9df2c819086f55f8bcf7f382e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69f80b62c8190bf2af2be0d3a7df8 |
completed | May 3, 2026, 1:06 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
| PDg | Predicate description generation | batch_69f69dfbf6ac8190ba2e6fc0adfd8b73 |
completed | May 3, 2026, 12:59 a.m. |
Created at: April 29, 2026, 8:47 p.m.