Triple
T6619610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zielona Góra |
E149641
|
entity |
| Predicate | twinCity |
P1072
|
FINISHED |
| Object | Lorient |
E153357
|
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: Lorient | Statement: [Zielona Góra, twinCity, Lorient]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lorient Context triple: [Zielona Góra, twinCity, Lorient]
-
A.
Lorient
chosen
Lorient is a port city in the Brittany region of northwestern France, known for its maritime heritage and annual Interceltic Festival.
-
B.
Concarneau
Concarneau is a coastal town and fishing port in Brittany, France, known for its walled medieval "Ville Close" and maritime heritage.
-
C.
Libourne
Libourne is a commune in southwestern France’s Gironde department, known as a wine-trading center and gateway to the Bordeaux wine region.
-
D.
Le Moule
Le Moule is a coastal commune and former sugar port on the island of Grande-Terre in Guadeloupe, known for its surfing beaches and colonial-era heritage.
-
E.
Luçon
Luçon is a historic town in western France, known as a former episcopal seat and for its notable cathedral and religious heritage.
- 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_69c687ed8a9c81908bb671717cb192ef |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6af5ca97481909f8a7dc47249b4d3 |
completed | March 27, 2026, 4:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7006cf9e881908a7cb7a8209ed7d2 |
completed | March 27, 2026, 10:10 p.m. |
Created at: March 27, 2026, 1:58 p.m.