Triple
T20941358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nantes bus network |
E515727
|
entity |
| Predicate | primaryHub |
P394
|
FINISHED |
| Object |
Graslin
Graslin is a central public square and transport hub in Nantes, France, known for its historic Théâtre Graslin and role as a key node in the city’s transit network.
|
E1457759
|
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: Graslin | Statement: [Nantes bus network, primaryHub, Graslin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Graslin Context triple: [Nantes bus network, primaryHub, Graslin]
-
A.
Lewis Greifer
Lewis Greifer was a British television and film writer known for his work on mid-20th-century dramas and genre series, including contributions to Doctor Who.
-
B.
Ardan
Ardan is a fictional character portrayed by Northern Irish actor Colin Morgan, known for his work in film, television, and theatre.
-
C.
Rose Tico
Rose Tico is a Resistance mechanic-turned-hero in the Star Wars sequel trilogy who fights alongside Finn against the First Order.
-
D.
Logan Sky
Logan Sky is a musician best known as a member of the synth-pop band Visage.
-
E.
Guion
Guion is a surname of French origin historically associated with several notable families and individuals.
- 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: Graslin Triple: [Nantes bus network, primaryHub, Graslin]
Generated description
Graslin is a central public square and transport hub in Nantes, France, known for its historic Théâtre Graslin and role as a key node in the city’s transit network.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Graslin Target entity description: Graslin is a central public square and transport hub in Nantes, France, known for its historic Théâtre Graslin and role as a key node in the city’s transit network.
-
A.
Lewis Greifer
Lewis Greifer was a British television and film writer known for his work on mid-20th-century dramas and genre series, including contributions to Doctor Who.
-
B.
Ardan
Ardan is a fictional character portrayed by Northern Irish actor Colin Morgan, known for his work in film, television, and theatre.
-
C.
Rose Tico
Rose Tico is a Resistance mechanic-turned-hero in the Star Wars sequel trilogy who fights alongside Finn against the First Order.
-
D.
Logan Sky
Logan Sky is a musician best known as a member of the synth-pop band Visage.
-
E.
Guion
Guion is a surname of French origin historically associated with several notable families and individuals.
- 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_69e0b4fc13408190b06868df03c5c29b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f955f0148190ae42278ad5c0f363 |
completed | April 21, 2026, 4:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a091fd8a17c819089f7af8ff6048ece |
completed | May 17, 2026, 1:54 a.m. |
| NEDg | Description generation | batch_6a09210bde4c8190841af0f9a29ecdd9 |
completed | May 17, 2026, 1:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09217fdcd08190bc41700ec09851e1 |
completed | May 17, 2026, 2:01 a.m. |
Created at: April 16, 2026, 12:50 p.m.