Triple
T5726709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lyon Metro Line B |
E126282
|
entity |
| Predicate | rollingStock |
P1305
|
FINISHED |
| Object |
MPL 16
MPL 16 is a modern automated rubber-tyred metro train used on Lyon’s Line B as part of the network’s upgraded driverless rolling stock.
|
E539415
|
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: MPL 16 | Statement: [Lyon Metro Line B, rollingStock, MPL 16]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MPL 16 Context triple: [Lyon Metro Line B, rollingStock, MPL 16]
-
A.
MPL
MPL is the IATA airport code for Montpellier-Méditerranée Airport, serving the city of Montpellier in southern France.
-
B.
MP 14
MP 14 is a modern rubber-tyred train model used on the Paris Métro, designed for improved energy efficiency, automation, and passenger comfort.
-
C.
MPL Communications
MPL Communications is Paul McCartney’s multimedia entertainment company that manages music publishing, copyrights, and other creative assets.
-
D.
1st MLG
1st MLG is a major logistics formation of the United States Marine Corps responsible for providing comprehensive combat service support to Marine Air-Ground Task Forces.
-
E.
M-1
M-1 is a state trunkline highway in Michigan, best known as Woodward Avenue, a major historic thoroughfare running through the Detroit metropolitan area.
- 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: MPL 16 Triple: [Lyon Metro Line B, rollingStock, MPL 16]
Generated description
MPL 16 is a modern automated rubber-tyred metro train used on Lyon’s Line B as part of the network’s upgraded driverless rolling stock.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MPL 16 Target entity description: MPL 16 is a modern automated rubber-tyred metro train used on Lyon’s Line B as part of the network’s upgraded driverless rolling stock.
-
A.
MPL
MPL is the IATA airport code for Montpellier-Méditerranée Airport, serving the city of Montpellier in southern France.
-
B.
MP 14
MP 14 is a modern rubber-tyred train model used on the Paris Métro, designed for improved energy efficiency, automation, and passenger comfort.
-
C.
MPL Communications
MPL Communications is Paul McCartney’s multimedia entertainment company that manages music publishing, copyrights, and other creative assets.
-
D.
1st MLG
1st MLG is a major logistics formation of the United States Marine Corps responsible for providing comprehensive combat service support to Marine Air-Ground Task Forces.
-
E.
M-1
M-1 is a state trunkline highway in Michigan, best known as Woodward Avenue, a major historic thoroughfare running through the Detroit metropolitan area.
- 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_69c0082f723881908ce8bb13a0c0f8b7 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0250a7f6c8190a264935086608186 |
completed | March 22, 2026, 5:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c05a86eea0819090bf6f9952d8dcc9 |
completed | March 22, 2026, 9:09 p.m. |
| NEDg | Description generation | batch_69c05cabceac819095c4a114220efb1a |
completed | March 22, 2026, 9:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c05d30463481909876ca02516d31cc |
completed | March 22, 2026, 9:20 p.m. |
Created at: March 22, 2026, 3:47 p.m.