Triple
T15186533
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marienburg Castle |
E362890
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Malbork |
E142537
|
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: Malbork | Statement: [Marienburg Castle, locatedIn, Malbork]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Malbork Context triple: [Marienburg Castle, locatedIn, Malbork]
-
A.
Malbork
chosen
Malbork is a historic town in northern Poland best known for the vast medieval Malbork Castle, one of the largest brick castles in the world and a UNESCO World Heritage Site.
-
B.
Chełmno
Chełmno is a historic town in northern Poland, known for its well-preserved medieval Old Town and Gothic architecture.
-
C.
Swarzewo
Swarzewo is a village in northern Poland, located near the Baltic Sea coast in the Pomeranian Voivodeship.
-
D.
Elbląg
Elbląg is a historic city in northern Poland known for its reconstructed Old Town, medieval heritage, and role as an important port and industrial center.
-
E.
Danzig
Danzig is an American heavy metal band formed by singer Glenn Danzig, known for its dark, blues-influenced sound and songs like "Mother."
- 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_69d85a09a39c81908759f23268e2d408 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e0067995fc8190b048f15086bd42f0 |
completed | April 15, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fec895b59c81908a09f8393a35aa13 |
completed | May 9, 2026, 5:39 a.m. |
Created at: April 10, 2026, 3:09 a.m.