Triple
T5885191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marius Pontmercy |
E130843
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object |
Rue Plumet
Rue Plumet is the quiet Parisian street in Victor Hugo’s *Les Misérables* where Marius and Cosette secretly meet and their love story unfolds.
|
E688626
|
NE FINISHED |
How this triple was built (4 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: Rue Plumet | Statement: [Marius Pontmercy, associatedWith, Rue Plumet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rue Plumet Context triple: [Marius Pontmercy, associatedWith, Rue Plumet]
-
A.
Rue Bergère
Rue Bergère is a street in Paris, France, historically notable for giving its name to the famous Folies Bergère music hall.
-
B.
Rue Belliard
Rue Belliard is a major street in Brussels’ European Quarter, lined with EU institutions, offices, and diplomatic buildings.
-
C.
Rue Pavée
Rue Pavée is a historic street in Paris’s Marais district, known for its old urban fabric and former role as the site of notable institutions and landmarks.
-
D.
Rue Feydeau
Rue Feydeau is a street in central Paris, France, historically notable for hosting the prominent Théâtre Feydeau.
-
E.
Rue André Pascal
Rue André Pascal is a street in Paris, France, known for hosting important institutions such as the Château de la Muette and the headquarters of the OECD.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Rue Plumet Triple: [Marius Pontmercy, associatedWith, Rue Plumet]
Generated description
Rue Plumet is the quiet Parisian street in Victor Hugo’s *Les Misérables* where Marius and Cosette secretly meet and their love story unfolds.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Rue Plumet Target entity description: Rue Plumet is the quiet Parisian street in Victor Hugo’s *Les Misérables* where Marius and Cosette secretly meet and their love story unfolds.
-
A.
Rue Bergère
Rue Bergère is a street in Paris, France, historically notable for giving its name to the famous Folies Bergère music hall.
-
B.
Rue Belliard
Rue Belliard is a major street in Brussels’ European Quarter, lined with EU institutions, offices, and diplomatic buildings.
-
C.
Rue Pavée
Rue Pavée is a historic street in Paris’s Marais district, known for its old urban fabric and former role as the site of notable institutions and landmarks.
-
D.
Rue Feydeau
Rue Feydeau is a street in central Paris, France, historically notable for hosting the prominent Théâtre Feydeau.
-
E.
Rue André Pascal
Rue André Pascal is a street in Paris, France, known for hosting important institutions such as the Château de la Muette and the headquarters of the OECD.
- F. None of above. chosen
Provenance (5 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_69c0085628dc8190b334c1b44c067efc |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0367743508190bae211e9ce8f9690 |
completed | March 22, 2026, 6:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8de86454081909232f45fa7d48976 |
completed | March 29, 2026, 8:10 a.m. |
| NEDg | Description generation | batch_69c8df95d77c8190abb80b9b59f20ee3 |
completed | March 29, 2026, 8:15 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8e037620c8190aa5948b68756793d |
completed | March 29, 2026, 8:17 a.m. |
Created at: March 22, 2026, 3:57 p.m.