Triple
T20101069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line 2 (Lille Metro) |
E496538
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object |
Porte de Douai
Porte de Douai is a metro station in Lille, France, serving passengers on the city’s automated rapid transit network.
|
E1413974
|
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: Porte de Douai | Statement: [Line 2 (Lille Metro), hasStation, Porte de Douai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Porte de Douai Context triple: [Line 2 (Lille Metro), hasStation, Porte de Douai]
-
A.
Porte de France
Porte de France, also known as Bab El Bhar, is a historic city gate in Tunis that once marked the boundary between the old medina and the modern European-style city.
-
B.
Porte de France
Porte de France is a historic city gate and fortification in Gravelines, France, notable for its role in the town’s defensive walls.
-
C.
Porte de Bourgogne
Porte de Bourgogne is a historic stone city gate in the medieval town of Moret-sur-Loing in north-central France.
-
D.
Porte d'Arras
Porte d'Arras is a metro station in Lille, France, serving the city's automated light metro network.
-
E.
Porte de Sens
Porte de Sens is a historic city gate in Villeneuve-sur-Yonne, France, notable as part of the town’s medieval fortifications.
- 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: Porte de Douai Triple: [Line 2 (Lille Metro), hasStation, Porte de Douai]
Generated description
Porte de Douai is a metro station in Lille, France, serving passengers on the city’s automated rapid transit network.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Porte de Douai Target entity description: Porte de Douai is a metro station in Lille, France, serving passengers on the city’s automated rapid transit network.
-
A.
Porte de France
Porte de France, also known as Bab El Bhar, is a historic city gate in Tunis that once marked the boundary between the old medina and the modern European-style city.
-
B.
Porte de France
Porte de France is a historic city gate and fortification in Gravelines, France, notable for its role in the town’s defensive walls.
-
C.
Porte de Bourgogne
Porte de Bourgogne is a historic stone city gate in the medieval town of Moret-sur-Loing in north-central France.
-
D.
Porte d'Arras
Porte d'Arras is a metro station in Lille, France, serving the city's automated light metro network.
-
E.
Porte de Sens
Porte de Sens is a historic city gate in Villeneuve-sur-Yonne, France, notable as part of the town’s medieval fortifications.
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6666ff4008190ae1eec907c89bd3b |
completed | April 20, 2026, 5:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a082dcee3088190b4d7f37bd2652bc6 |
completed | May 16, 2026, 8:41 a.m. |
| NEDg | Description generation | batch_6a082f11c60c81909b112216661b85fe |
completed | May 16, 2026, 8:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0830b3d9c08190a78ace19148a3bdd |
completed | May 16, 2026, 8:54 a.m. |
Created at: April 11, 2026, 11:26 p.m.