Triple
T9732229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Métro Line 3 |
E235772
|
entity |
| Predicate | depot |
P14646
|
FINISHED |
| Object |
Saint-Fargeau depot
Saint-Fargeau depot is a maintenance and storage facility for trains operating on Paris Métro Line 3.
|
E816333
|
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: Saint-Fargeau depot | Statement: [Paris Métro Line 3, depot, Saint-Fargeau depot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint-Fargeau depot Context triple: [Paris Métro Line 3, depot, Saint-Fargeau depot]
-
A.
Fontenay-sous-Bois depot
Fontenay-sous-Bois depot is a maintenance and storage facility serving trains on Paris Métro Line 1, located in the eastern suburb of Fontenay-sous-Bois.
-
B.
Châtillon-Montrouge depot
Châtillon-Montrouge depot is a major Paris Métro maintenance and storage facility, notably serving rolling stock such as the MF 77 trains.
-
C.
Cronenbourg depot
Cronenbourg depot is a major maintenance and storage facility for the Strasbourg tramway network in Strasbourg, France.
-
D.
Nevers railway depot
Nevers railway depot is a railway maintenance and stabling facility in Nevers, France, serving trains operating through the Nevers railway station.
-
E.
Pontinha depot
Pontinha depot is a maintenance and storage facility serving the Lisbon Metro system in Lisbon, Portugal.
- 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: Saint-Fargeau depot Triple: [Paris Métro Line 3, depot, Saint-Fargeau depot]
Generated description
Saint-Fargeau depot is a maintenance and storage facility for trains operating on Paris Métro Line 3.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Saint-Fargeau depot Target entity description: Saint-Fargeau depot is a maintenance and storage facility for trains operating on Paris Métro Line 3.
-
A.
Fontenay-sous-Bois depot
Fontenay-sous-Bois depot is a maintenance and storage facility serving trains on Paris Métro Line 1, located in the eastern suburb of Fontenay-sous-Bois.
-
B.
Châtillon-Montrouge depot
Châtillon-Montrouge depot is a major Paris Métro maintenance and storage facility, notably serving rolling stock such as the MF 77 trains.
-
C.
Cronenbourg depot
Cronenbourg depot is a major maintenance and storage facility for the Strasbourg tramway network in Strasbourg, France.
-
D.
Nevers railway depot
Nevers railway depot is a railway maintenance and stabling facility in Nevers, France, serving trains operating through the Nevers railway station.
-
E.
Pontinha depot
Pontinha depot is a maintenance and storage facility serving the Lisbon Metro system in Lisbon, Portugal.
- 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_69ca84d0fad481909cdd45aa77416c48 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9eb3d6e4819090b3c7fb92550c57 |
completed | April 1, 2026, 10:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d19fbbba2081909a15725a68423162 |
completed | April 4, 2026, 11:33 p.m. |
| NEDg | Description generation | batch_69d1a065ce008190985b792302daa7cb |
completed | April 4, 2026, 11:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1a0f811fc8190b6a46a0441159089 |
completed | April 4, 2026, 11:38 p.m. |
Created at: March 30, 2026, 8:22 p.m.