Triple
T36294710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | German U-boat U-20 |
E893324
|
entity |
| Predicate | locationOfLusitaniaSinking |
P3148
|
FINISHED |
| Object | off the Old Head of Kinsale, Ireland |
—
|
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: off the Old Head of Kinsale, Ireland | Statement: [German U-boat U-20, locationOfLusitaniaSinking, off the Old Head of Kinsale, Ireland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOfLusitaniaSinking Context triple: [German U-boat U-20, locationOfLusitaniaSinking, off the Old Head of Kinsale, Ireland]
-
A.
routeAtTimeOfSinking
Indicates the specific route an entity (such as a vessel) was following at the time it sank.
-
B.
placeOfSinking
chosen
Indicates the location where an object or entity sank or was submerged.
-
C.
distanceFromMaltaAtSinking
Indicates the measured distance between a vessel’s location and Malta at the time the vessel sank.
-
D.
wreckLocated
Indicates that the location of a wreck (such as a destroyed vehicle, ship, or structure) is specified or associated with a particular place or area.
-
E.
locationDuringBattleOfJutland
Indicates the geographic place where an entity was situated during the time of the Battle of Jutland.
- 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_69f76e4a61f0819084a2b68dbbb4efc6 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:09 p.m.