Triple
T14019740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. Marien Church |
E337296
|
entity |
| Predicate | hasNameInLanguage |
P15
|
FINISHED |
| Object | Sankt Marien Kirche |
unclear NED1
|
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: Sankt Marien Kirche | Statement: [St. Marien Church, hasNameInLanguage, Sankt Marien Kirche]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sankt Marien Kirche Context triple: [St. Marien Church, hasNameInLanguage, Sankt Marien Kirche]
-
A.
St. Marien church
St. Marien church is a historic Christian church and prominent architectural landmark located in the town of Marienberg, Germany.
-
B.
St. Marien church
St. Marien church is a historic Christian church and notable architectural landmark located in Roßlau (Elbe), Germany.
-
C.
Christophoruskirche
Christophoruskirche is a historic Christian church and local landmark in the town of Altenau in Germany’s Harz region.
-
D.
Martinskirche
Martinskirche is a historic church and prominent architectural landmark in the German town of Ladenburg.
-
E.
St. Mary’s Church (Marienkirche)
St. Mary’s Church (Marienkirche) is a historic Gothic brick church in Anklam, Germany, notable for its medieval architecture and prominent tower.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d81c6543a48190bd5ba93d7419e797 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2f3c7cd88190b236382058581740 |
completed | April 14, 2026, 12:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbc32d77108190b038e8a750738439 |
completed | May 6, 2026, 10:39 p.m. |
Created at: April 9, 2026, 10:19 p.m.