Triple
T6644279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nivernais |
E150661
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Nevers |
E172114
|
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: Nevers | Statement: [Nivernais, capital, Nevers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nevers Context triple: [Nivernais, capital, Nevers]
-
A.
Nevers
chosen
Nevers is a historic city in central France known for its medieval architecture, religious heritage, and traditional faience pottery.
-
B.
Toul
Toul is a historic commune in northeastern France known for its medieval fortifications and impressive Gothic cathedral.
-
C.
Villeurbannais
Villeurbannais is the French term for an inhabitant or native of the city of Villeurbanne, located near Lyon in eastern France.
-
D.
Deauzya
Deauzya is the given first name of American professional basketball player DiDi Richards.
-
E.
Belfort
Belfort is the surname of Jordan Belfort, the American former stockbroker, motivational speaker, and author whose high-profile fraud case inspired the film "The Wolf of Wall Street."
- 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_69c687f1a3048190828b7342f7125d5c |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6b01a53388190a31f6624d6f60faa |
completed | March 27, 2026, 4:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6eef22e58819097bd6533c157d454 |
completed | March 27, 2026, 8:56 p.m. |
Created at: March 27, 2026, 2 p.m.