Triple
T8152400
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 20th arrondissement of Paris |
E190362
|
entity |
| Predicate | borderedBy |
P224
|
FINISHED |
| Object |
Seine-Saint-Denis department (to the northeast)
Seine-Saint-Denis is a densely populated suburban department in the Île-de-France region, known for its cultural diversity, working-class communities, and location just northeast of central Paris.
|
E717532
|
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: Seine-Saint-Denis department (to the northeast) | Statement: [20th arrondissement of Paris, borderedBy, Seine-Saint-Denis department (to the northeast)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Seine-Saint-Denis department (to the northeast) Context triple: [20th arrondissement of Paris, borderedBy, Seine-Saint-Denis department (to the northeast)]
-
A.
Nord department
Nord department is an administrative region in northern France bordering Belgium, known for its industrial heritage and historic cities such as Lille.
-
B.
Nord department
The Nord department is an administrative region in northern Haiti known for its historic cities, including Cap-Haïtien, and its significant role in the country’s colonial and revolutionary history.
-
C.
Department of Hauts-de-Seine
The Department of Hauts-de-Seine is an administrative division in the western suburbs of Paris, France, known for its affluent communities and major business districts such as La Défense.
-
D.
Seine-et-Oise department
Seine-et-Oise was a former department of France surrounding Paris that existed from the French Revolution until its 1968 breakup into several new departments, including Val-de-Marne.
-
E.
Val-d'Oise department
Val-d'Oise department is an administrative division in the Île-de-France region of northern France that includes both suburban areas of Paris and major transport hubs such as Charles de Gaulle Airport.
- 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: Seine-Saint-Denis department (to the northeast) Triple: [20th arrondissement of Paris, borderedBy, Seine-Saint-Denis department (to the northeast)]
Generated description
Seine-Saint-Denis is a densely populated suburban department in the Île-de-France region, known for its cultural diversity, working-class communities, and location just northeast of central Paris.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Seine-Saint-Denis department (to the northeast) Target entity description: Seine-Saint-Denis is a densely populated suburban department in the Île-de-France region, known for its cultural diversity, working-class communities, and location just northeast of central Paris.
-
A.
Nord department
Nord department is an administrative region in northern France bordering Belgium, known for its industrial heritage and historic cities such as Lille.
-
B.
Nord department
The Nord department is an administrative region in northern Haiti known for its historic cities, including Cap-Haïtien, and its significant role in the country’s colonial and revolutionary history.
-
C.
Department of Hauts-de-Seine
The Department of Hauts-de-Seine is an administrative division in the western suburbs of Paris, France, known for its affluent communities and major business districts such as La Défense.
-
D.
Seine-et-Oise department
Seine-et-Oise was a former department of France surrounding Paris that existed from the French Revolution until its 1968 breakup into several new departments, including Val-de-Marne.
-
E.
Val-d'Oise department
Val-d'Oise department is an administrative division in the Île-de-France region of northern France that includes both suburban areas of Paris and major transport hubs such as Charles de Gaulle Airport.
- 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_69ca82be7ba8819087de0147e9292c83 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb44d4494c8190aad2ee302e90670f |
completed | March 31, 2026, 3:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbef9f28881909961b599d395d6df |
completed | April 1, 2026, 6:45 a.m. |
| NEDg | Description generation | batch_69ccc310b514819099228a1cc66517c5 |
completed | April 1, 2026, 7:02 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ccd8041c00819094094701ace21aa0 |
completed | April 1, 2026, 8:32 a.m. |
Created at: March 30, 2026, 5:37 p.m.