Triple
T20378530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris-Austerlitz |
E497755
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Orléans |
—
|
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: Orléans | Statement: [Paris-Austerlitz, connectsTo, Orléans]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Orléans Context triple: [Paris-Austerlitz, connectsTo, Orléans]
-
A.
Orléans
Orléans is a federal electoral district in the eastern part of Ottawa, Ontario, represented in the House of Commons of Canada.
-
B.
Orléans
chosen
Orléans is a historic city in north-central France, renowned for its association with Joan of Arc and its location on the Loire River.
-
C.
Orleans
Orleans is a coastal town on outer Cape Cod in Massachusetts known for its beaches, fishing, and role as a popular summer vacation destination.
-
D.
Orleans
Orleans is a white grape variety used in European wine production, historically cultivated in regions such as Germany and Central Europe.
-
E.
Orleans
Orleans is an American soft rock band best known for 1970s hits like "Still the One" and "Dance with Me."
- 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_69e0b4a5b7908190a972e4e7e698ae94 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678af651c8190b4922294a937e699 |
completed | April 20, 2026, 7:04 p.m. |
Created at: April 16, 2026, 11:27 a.m.