Triple
T14425967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German U-boat U-47 |
E357698
|
entity |
| Predicate | dateSankHMSRoyalOak |
P114227
|
FINISHED |
| Object | 14 October 1939 |
—
|
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: 14 October 1939 | Statement: [German U-boat U-47, dateSankHMSRoyalOak, 14 October 1939]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateSankHMSRoyalOak Context triple: [German U-boat U-47, dateSankHMSRoyalOak, 14 October 1939]
-
A.
chronometerNumber
Indicates that an entity has been assigned a specific chronometer identification number, linking it to that unique timekeeping device record.
-
B.
watchmaking
Indicates the action or process of designing, assembling, and adjusting watches or timekeeping mechanisms.
-
C.
clockFaceDate
Indicates that a specific date is shown or represented on the face of a clock or clock-like display.
-
D.
watchMovementType
Indicates the type of mechanical or electronic movement mechanism that drives how a watch operates.
-
E.
watches
Indicates that one entity observes or views another entity or event, typically by looking at it attentively over a period of time.
- 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_69d8279402a88190821ffa39ae15bccf |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de911398f08190be85bc0a8bef6b1b |
completed | April 14, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69de5c30467881908e770e3940295641 |
completed | April 14, 2026, 3:24 p.m. |
| PDg | Predicate description generation | batch_69de5fb4de14819092acdecbd201d672 |
completed | April 14, 2026, 3:39 p.m. |
Created at: April 10, 2026, 1:18 a.m.