Triple
T3288070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ultra-Trail du Mont-Blanc |
E69033
|
entity |
| Predicate | coFounder |
P2835
|
FINISHED |
| Object |
Jean-Claude Marmier
Jean-Claude Marmier is a French trail-running organizer best known as one of the founders of the prestigious Ultra-Trail du Mont-Blanc mountain ultramarathon.
|
E525033
|
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: Jean-Claude Marmier | Statement: [Ultra-Trail du Mont-Blanc, coFounder, Jean-Claude Marmier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jean-Claude Marmier Context triple: [Ultra-Trail du Mont-Blanc, coFounder, Jean-Claude Marmier]
-
A.
Jean-Michel Raimond
Jean-Michel Raimond is a French physicist known for his work in quantum optics and cavity quantum electrodynamics.
-
B.
Michel Andrault
Michel Andrault was a prominent French architect known for his influential large-scale housing and urban development projects in the late 20th century.
-
C.
Michel Harmand
Michel Harmand is an automotive designer best known for his work on the innovative and aerodynamically styled Citroën CX.
-
D.
Roland Gallois
Roland Gallois is a film editor known for his work on the feature film "Slow West."
-
E.
Jean-Claude Olivier
Jean-Claude Olivier is a writer associated with the Juicy brand or publication.
- 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: Jean-Claude Marmier Triple: [Ultra-Trail du Mont-Blanc, coFounder, Jean-Claude Marmier]
Generated description
Jean-Claude Marmier is a French trail-running organizer best known as one of the founders of the prestigious Ultra-Trail du Mont-Blanc mountain ultramarathon.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jean-Claude Marmier Target entity description: Jean-Claude Marmier is a French trail-running organizer best known as one of the founders of the prestigious Ultra-Trail du Mont-Blanc mountain ultramarathon.
-
A.
Jean-Michel Raimond
Jean-Michel Raimond is a French physicist known for his work in quantum optics and cavity quantum electrodynamics.
-
B.
Michel Andrault
Michel Andrault was a prominent French architect known for his influential large-scale housing and urban development projects in the late 20th century.
-
C.
Michel Harmand
Michel Harmand is an automotive designer best known for his work on the innovative and aerodynamically styled Citroën CX.
-
D.
Roland Gallois
Roland Gallois is a film editor known for his work on the feature film "Slow West."
-
E.
Jean-Claude Olivier
Jean-Claude Olivier is a writer associated with the Juicy brand or publication.
- 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_69ad859d45748190b0742408c954b39f |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb058e00881908fdf0a23208860d4 |
completed | March 8, 2026, 5:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf832772d08190842b1e1c1a87ea3a |
completed | March 22, 2026, 5:50 a.m. |
| NEDg | Description generation | batch_69bf83e188888190bbc058b0e27125aa |
completed | March 22, 2026, 5:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf844f7be0819089a1cbb3b8c41e0b |
completed | March 22, 2026, 5:55 a.m. |
Created at: March 8, 2026, 3:10 p.m.