Triple
T2042884
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pont Neuf |
E44783
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Île de la Cité |
E43231
|
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: Île de la Cité | Statement: [Pont Neuf, connects, Île de la Cité]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Île de la Cité Context triple: [Pont Neuf, connects, Île de la Cité]
-
A.
Île de la Cité
chosen
Île de la Cité is a historic island in the Seine at the heart of Paris, regarded as the city's medieval and spiritual center.
-
B.
Marbeuf
Marbeuf was an early name used by Franklin D. Roosevelt before he became widely known under his given name as the 32nd president of the United States.
-
C.
Ile de Puteaux
Île de Puteaux is a small Seine River island in the western suburbs of Paris, known for its sports facilities and role as a venue during the 1900 Summer Olympics.
-
D.
Fontvieille
Fontvieille is a modern district of Monaco built largely on reclaimed land, known for its marina, residential complexes, and commercial facilities.
-
E.
Châtelet–Les Halles
Châtelet–Les Halles is a major underground transport hub in central Paris, serving as one of the largest and busiest railway and metro stations in Europe.
- 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_69a889159ec481908f9e4472d9f480c7 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb96f932881908bebfc4176fda7c0 |
completed | March 7, 2026, 5:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae5181998c819098dd5a7fd3c5757c |
completed | March 9, 2026, 4:50 a.m. |
Created at: March 4, 2026, 7:39 p.m.