Triple
T9875938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quartier de Bel-Air |
E240071
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object | Porte Dorée |
E799410
|
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: Porte Dorée | Statement: [Quartier de Bel-Air, hasLandmark, Porte Dorée]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Porte Dorée Context triple: [Quartier de Bel-Air, hasLandmark, Porte Dorée]
-
A.
Porte Dorée
Porte Dorée is an ornate historic gateway of the Château de Fontainebleau, notable for its richly decorated Renaissance architecture.
-
B.
Porte Dorée
chosen
Porte Dorée is a Parisian neighborhood and metro area in the 12th arrondissement, known for its proximity to the Bois de Vincennes and the Palais de la Porte Dorée.
-
C.
Porte de Paris
Porte de Paris is a historic city gate in Cambrai, France, notable for its monumental architecture and role as a former entrance to the fortified town.
-
D.
Porte Dauphine
Porte Dauphine is a Paris Métro station on Line 2, located near the Bois de Boulogne in the 16th arrondissement of Paris.
-
E.
Porte de l’Oulle
Porte de l’Oulle is a historic city gate in Avignon, France, forming part of the medieval fortifications that once protected the city.
- 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_69ca84e8a0788190b9061811d50fd554 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3f9d82c81908afb4977ce4e3e4a |
completed | April 2, 2026, 12:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1e47b62388190a033743376500375 |
completed | April 5, 2026, 4:26 a.m. |
Created at: March 30, 2026, 8:37 p.m.