Triple
T21198101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nantes–Pornic railway |
E522377
|
entity |
| Predicate | hasEndpointTown |
P847
|
FINISHED |
| Object | Pornic |
—
|
NE NERFINISHED |
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: Pornic | Statement: [Nantes–Pornic railway, hasEndpointTown, Pornic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pornic Context triple: [Nantes–Pornic railway, hasEndpointTown, Pornic]
-
A.
Pornic
chosen
Pornic is a coastal resort town and fishing port on the Atlantic Ocean in western France, known for its scenic harbor, beaches, and medieval castle.
-
B.
Pornic marina
Pornic marina is a coastal harbor and leisure port in the town of Pornic on France’s Atlantic coast, serving recreational boats and supporting local tourism.
-
C.
Pitești
Pitești is a city in southern Romania, known as an important industrial and transportation hub and the capital of Argeș County.
-
D.
Târgu Ocna
Târgu Ocna is a town in Bacău County, Romania, known for its historic salt mine and spa tourism in the Trotuș Valley.
-
E.
Telenești
Telenești is a town in central Moldova known as the administrative center of Telenești District.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b51061388190aa03f19700d3ef04 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7333d6dec8190bbc66a71b31ea559 |
completed | April 21, 2026, 8:20 a.m. |
Created at: April 16, 2026, 3:16 p.m.