Triple
T14759872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gare de Saint-Cloud |
E346828
|
entity |
| Predicate | railwayLine |
P848
|
FINISHED |
| Object |
Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly
Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly is a suburban railway line in the western Paris region that connects the Saint-Lazare terminus to the town of Saint-Nom-la-Bretèche via several intermediate stations.
|
E1119574
|
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: Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly | Statement: [Gare de Saint-Cloud, railwayLine, Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly Context triple: [Gare de Saint-Cloud, railwayLine, Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly]
-
A.
Transilien Paris–Saint-Lazare suburban rail network (via nearby stations)
The Transilien Paris–Saint-Lazare suburban rail network is a regional commuter rail system radiating from Paris Saint-Lazare station that connects Paris with numerous western suburbs and towns in the Île-de-France region.
-
B.
Paris–Mantes-la-Jolie via Poissy railway
The Paris–Mantes-la-Jolie via Poissy railway is a suburban rail route in the Île-de-France region that connects central Paris with the town of Mantes-la-Jolie through Poissy, serving as part of the regional Transilien commuter network.
-
C.
Transilien Paris–Saint-Lazare suburban rail network
The Transilien Paris–Saint-Lazare suburban rail network is a regional commuter rail system radiating from Paris Saint-Lazare station, connecting Paris with numerous western and northwestern suburbs and towns in the Île-de-France region.
-
D.
Paris Métro Line 3bis at Père Lachaise
Paris Métro Line 3bis at Père Lachaise is a short branch line of the Paris Métro serving the Père Lachaise area and connecting with other major lines in the network.
-
E.
Paris Métro Line 1 at Porte Maillot
Paris Métro Line 1 at Porte Maillot is a major station on one of Paris’s busiest automated metro lines, serving as a key transport hub near the Palais des Congrès and the western edge of the city.
- 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: Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly Triple: [Gare de Saint-Cloud, railwayLine, Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly]
Generated description
Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly is a suburban railway line in the western Paris region that connects the Saint-Lazare terminus to the town of Saint-Nom-la-Bretèche via several intermediate stations.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly Target entity description: Ligne de Paris-Saint-Lazare à Saint-Nom-la-Bretèche–Forêt de Marly is a suburban railway line in the western Paris region that connects the Saint-Lazare terminus to the town of Saint-Nom-la-Bretèche via several intermediate stations.
-
A.
Transilien Paris–Saint-Lazare suburban rail network (via nearby stations)
The Transilien Paris–Saint-Lazare suburban rail network is a regional commuter rail system radiating from Paris Saint-Lazare station that connects Paris with numerous western suburbs and towns in the Île-de-France region.
-
B.
Paris–Mantes-la-Jolie via Poissy railway
The Paris–Mantes-la-Jolie via Poissy railway is a suburban rail route in the Île-de-France region that connects central Paris with the town of Mantes-la-Jolie through Poissy, serving as part of the regional Transilien commuter network.
-
C.
Transilien Paris–Saint-Lazare suburban rail network
The Transilien Paris–Saint-Lazare suburban rail network is a regional commuter rail system radiating from Paris Saint-Lazare station, connecting Paris with numerous western and northwestern suburbs and towns in the Île-de-France region.
-
D.
Paris Métro Line 3bis at Père Lachaise
Paris Métro Line 3bis at Père Lachaise is a short branch line of the Paris Métro serving the Père Lachaise area and connecting with other major lines in the network.
-
E.
Paris Métro Line 1 at Porte Maillot
Paris Métro Line 1 at Porte Maillot is a major station on one of Paris’s busiest automated metro lines, serving as a key transport hub near the Palais des Congrès and the western edge of the city.
- 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_69d822e8896c819091169882f9b20486 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69dec7f0f5a48190af008352c26574d7 |
completed | April 14, 2026, 11:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe0cefb7c08190bf69b15165f046d0 |
completed | May 8, 2026, 4:18 p.m. |
| NEDg | Description generation | batch_69fe1a0e2820819092abfc2795ba4851 |
completed | May 8, 2026, 5:14 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fe1a89d4d08190a2be8b4b0bc5a472 |
completed | May 8, 2026, 5:16 p.m. |
Created at: April 10, 2026, 1:30 a.m.