Triple
T9540671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Regen (district) |
E230146
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Metten |
E272044
|
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: Metten | Statement: [Regen (district), contains, Metten]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Metten Context triple: [Regen (district), contains, Metten]
-
A.
Metten
chosen
Metten is a small Bavarian town in Germany, known for its historic Benedictine abbey and traditional Bavarian character.
-
B.
Roermond
Roermond is a historic city in the southeastern Netherlands known for its medieval architecture, prominent churches, and large designer outlet shopping center.
-
C.
Meerwijk
Meerwijk is a residential neighborhood within the town of Uithoorn in the province of North Holland, Netherlands.
-
D.
Turnhout
Turnhout is a historic city in northern Belgium known for its playing card industry, cultural heritage, and role as a regional center in the Kempen area.
-
E.
Heerlen
Heerlen is a city in the southeastern Netherlands known for its mining history and modernist architecture, located in the province of Limburg.
- 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_69ca847b1b3081908f72bc932c17cc41 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd98e695948190ab107fff38c57de7 |
completed | April 1, 2026, 10:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d14c6538b08190a9f81304214a876d |
completed | April 4, 2026, 5:37 p.m. |
Created at: March 30, 2026, 8:01 p.m.