Triple
T13271938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyon 2nd arrondissement |
E316081
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Place Carnot |
E383875
|
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: Place Carnot | Statement: [Lyon 2nd arrondissement, contains, Place Carnot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Place Carnot Context triple: [Lyon 2nd arrondissement, contains, Place Carnot]
-
A.
Place Carnot
chosen
Place Carnot is a central public square in Lyon, France, known for its statue of the Republic, frequent markets, and proximity to the Perrache transport hub.
-
B.
Place Boieldieu
Place Boieldieu is a small Parisian square in the 2nd arrondissement best known for hosting the historic Opéra-Comique theatre.
-
C.
Lugrin
Lugrin is a commune in eastern France on the southern shore of Lake Geneva, known historically as one of the sites where the Évian Accords negotiations took place.
-
D.
Place Jean-Jaurès
Place Jean-Jaurès is a public square in France named in honor of the socialist leader and statesman Jean Jaurès.
-
E.
Hautepierre
Hautepierre is a residential district in the western part of Strasbourg, France, known for its large housing estates and local commercial centers.
- 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_69d806b1d9ac8190852c5571d5bd5f0f |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99020f710819094c2618662bdc7fd |
completed | April 11, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a51d458819080b8c8f3a4df0f52 |
completed | May 3, 2026, 8:41 a.m. |
Created at: April 9, 2026, 9:26 p.m.