Triple
T616016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Admiral Graf Spee |
E14405
|
entity |
| Predicate | placeBuilt |
P14101
|
FINISHED |
| Object | Wilhelmshaven |
E41561
|
NE 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: Wilhelmshaven | Statement: [Admiral Graf Spee, placeBuilt, Wilhelmshaven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wilhelmshaven Context triple: [Admiral Graf Spee, placeBuilt, Wilhelmshaven]
-
A.
Wilhelmshaven
chosen
Wilhelmshaven is a coastal city in northwestern Germany known for its major naval base and port on the North Sea.
-
B.
Dover
Dover is a small town in eastern Dutchess County, New York, known for its rural character and location near the Connecticut border.
-
C.
Dover
Dover is a coastal town in southeast England best known for its white chalk cliffs and its strategic port facing the narrowest part of the English Channel.
-
D.
Harwich
Harwich is a coastal town on southeastern Cape Cod in Massachusetts known for its beaches, harbors, and summer tourism.
-
E.
Lowestoft
Lowestoft is a coastal town in Suffolk, England, known as the easternmost settlement in the United Kingdom and a traditional fishing and seaside resort.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e0b438881909ad515adf7a4eb79 |
completed | March 1, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a7c000b64c819091140b7c3718acf6 |
completed | March 4, 2026, 5:15 a.m. |
Created at: March 1, 2026, 7:35 p.m.